IP Library › Granted Patent US 12,731,343
Granted Patent B2
US 12,731,343 · App. 18/340,736 · Granted Sep 8, 2026

Unifying densepose and 3D body mesh reconstruction

Inventors: Riza Alp Guler (London, GB); Antonios Kakolyris (London, GB); Iason Kokkinos (London, GB); Petros Koutras (London, GB); Eric-Tuan Le (London, GB); Georgios Papandreou (London, GB); Efstratios Skordos (London, GB); Himmy Tam (London, GB)
Assignee: SNAP INC.
G06T19/006G06T7/13G06T7/73G06T17/20G06T2207/20081G06T2207/20221G06T2207/30196G06T2210/12G06T2210/52
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,731,343
App. No.
18/340,736
Granted
Sep 8, 2026
Kind
B2
Abstract

Methods and systems are disclosed for generating a 3D body mesh. The system receives an image that includes a depiction of a real-world object in a real-world environment. The system applies a first machine learning model to a portion of the image that depicts the real-world object to predict a tensor of heatmaps representing vertex positions of a plurality of triangles of a 3D mesh corresponding to the real-world object. First and second heatmaps of the tensor represent respectively first and second groups of possible coordinates for a first vertex of a first triangle of the plurality of triangles. The system generates the 3D mesh based on the selected subset of the tensor of heatmaps.

Claims (69)

1 . A method comprising:

receiving an image that includes a depiction of a real-world object;

predicting a tensor of two-dimensional (2D) heatmaps by applying a first machine learning model to a portion of the image, each 2D heatmap of the tensor of 2D heatmaps exclusively representing possible positions for a corresponding single vertex of an individual triangle of a plurality of triangles of a three-dimensional (3D) mesh corresponding to the real-world object, the first machine learning model trained to predict a part of the 3D mesh that is not visible within the image including at least one of occluded vertices, self-occluded vertices, or truncated vertices, a first heatmap of the tensor of heatmaps representing a first group of possible coordinates exclusively for a single first vertex of a first triangle of the plurality of triangles, a second heatmap of the tensor of heatmaps representing a second group of possible coordinates exclusively for a single second vertex of the same first triangle as the first heatmap;

selecting a subset of the tensor of heatmaps from the tensor of heatmaps, the subset of the tensor of heatmaps comprising a first coordinate of the first group of possible coordinates and a second coordinate of the second group of possible coordinates; and

generating the 3D mesh based on the selected subset of the tensor of heatmaps, the 3D mesh being combined with an inpainted mesh to form a reconstructed 3D mesh.

2 . The method of claim 1 , further comprising:

predicting a plurality of bounding boxes for each of a plurality of real-world objects depicted in the image by applying a second machine learning model to the image; and

selecting a first bounding box from the plurality of bounding boxes to identify the portion of the image.

3 . The method of claim 1 , wherein the tensor of heatmaps represent a sparsepose corresponding to a range of possible vertices of a densepose.

4 . The method of claim 1 , wherein the 3D mesh comprises an initial 3D mesh, further comprising:

predicting a set of 3D key points corresponding to a skeleton of the real-world object by applying a second machine learning model to the portion of the image;

generating, in parallel with the initial 3D mesh, an intermediate 3D mesh using the set of 3D key points representing a per-vertex depth of the real-world object;

fusing the initial 3D mesh with the intermediate 3D mesh to form a reconstructed 3D mesh, wherein generating the intermediate 3D mesh comprises predicting an inverse depth for each vertex of the intermediate 3D mesh, the inverse depth correlated with an object scale of the real-world object, wherein predicting the inverse depth for each vertex comprises computing the inverse depth of a vertex based on an estimated inverse depth of a parent skeleton joint and a per-vertex inverse-depth offset predicted by the first machine learning model; and

un-projecting a vertex to a three-dimensional (3D) position using a focal length of a camera model and the predicted inverse depth.

5 . The method of claim 1 , further comprising training the first machine learning model using training data comprising a plurality of training images depicting real-world objects and corresponding ground-truth denseposes and training 3D meshes corresponding to the training real-world objects, each ground-truth densepose representing coordinates of respective 3D meshes of the training real-world objects, wherein training the first machine learning model comprises applying weak supervision for vertex depths when direct mesh supervision is unavailable.

6 . The method of claim 5 , further comprising training the first machine learning model by computing a plurality of losses.

7 . The method of claim 6 , wherein a first loss of the plurality of losses comprises a cross-entropy loss, further comprising:

obtaining a first training image of the plurality of training images and a first ground-truth densepose corresponding to a first training real-world object depicted in the first training image;

computing barycentric coordinates of an individual triangle of a training 3D mesh corresponding to a particular pixel of the first training real-world object using the first ground-truth densepose;

estimating an individual tensor of heatmaps corresponding to the first training real-world object by applying the first machine learning model to the first training image;

generating predicted posterior coordinates using a selection of a group of coordinates of the individual tensor of heatmaps corresponding to the particular pixel of the first training real-world object;

computing a deviation comprising the cross-entropy loss between the predicted posterior coordinates and the barycentric coordinates; and

updating parameters of the first machine learning model based on the deviation.

8 . The method of claim 7 , wherein each heatmap of the individual tensor of heatmaps represents a respective group of possible coordinates for an individual vertex of an individual triangle of an individual mesh corresponding to the first training real-world object, further comprising updating scores associated with the respective group of possible coordinates for the individual vertex based on the cross-entropy loss.

9 . The method of claim 8 , wherein a second loss of the plurality of losses comprises a vertex localization loss, further comprising:

integrating scores of the group of possible coordinates for each vertex of the individual mesh corresponding to the first training real-world object to generate estimated coordinates for each vertex of the individual mesh;

computing a deviation between a particular vertex of the estimated coordinates of the individual mesh and a corresponding vertex of a training 3D mesh of the first training real-world object; and

computing a first portion of the second loss based on the computed deviation between the particular vertex and the corresponding vertex.

10 . The method of claim 9 , further comprising:

computing a first edge based on a difference between a first pair of the estimated coordinates of a particular triangle of the individual mesh;

computing a second edge based on a difference between a second pair of coordinates of a corresponding triangle of the training 3D mesh; and

computing a second portion of the second loss based on a deviation between the first edge and the second edge.

11 . The method of claim 7 , wherein a second loss of the plurality of losses comprises a part segmentation loss, further comprising:

identifying a plurality of parts of the first training real-world object, each of the plurality of parts comprising a respective collection of triangles;

selecting a particular part of the plurality of parts;

retrieving a group of coordinates of the individual tensor of heatmaps corresponding to the particular part;

computing a sum of scores associated with the retrieved group of coordinates;

comparing the sum of the scores to a threshold; and

updating parameters of the first machine learning model based on a result of comparing the sum of the scores to the threshold to maximize the sum of the scores for the retrieved group of coordinates.

12 . The method of claim 7 , wherein a second loss of the plurality of losses comprises a spatial consistency loss, further comprising:

obtaining a ground-truth pixel value of the first training image for a given set of barycentric coordinates corresponding to the individual triangle of the training 3D mesh;

computing an estimated pixel value based on the predicted posterior coordinates; and

computing the spatial consistency loss based on a deviation between the ground-truth pixel value and the estimated pixel value.

13 . The method of claim 7 , further comprising:

applying a second machine learning model to the portion of the image to estimate offsets between vertices of the 3D mesh.

14 . The method of claim 13 , further comprising training the second machine learning model based on an offset loss by:

computing a first offset between first and second vertices of the training 3D mesh;

computing a second offset between first and second vertices of an individual mesh generated using the individual tensor of heatmaps; and

computing the offset loss based on a deviation between the first and second offsets.

15 . The method of claim 13 , wherein the second machine learning model estimates a depth of the 3D mesh.

16 . The method of claim 1 , wherein the subset of the tensor of heatmaps represents a set of vertices of the plurality of triangles each associated with a score that transgresses a threshold score, further comprising:

predicting a continuous UV field in an interior of the first triangle by interpolating between 2D vertex positions of the first triangle using barycentric coordinates, wherein the continuous UV field comprises a weighted combination of vertex UV values.

17 . The method of claim 1 , wherein generating the 3D mesh comprises:

adopting a perspective camera model where each vertex of the 3D mesh lies on a ray crossing an image plane at a two-dimensional (2D) position predicted from the tensor of 2D heatmaps; and

estimating a depth of each vertex along the ray.

18 . A system comprising:

at least one processor; and

at least one memory component having instructions stored thereon that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:

receiving an image that includes a depiction of a real-world object;

predicting a tensor of two-dimensional (2D) heatmaps by applying a first machine learning model to a portion of the image, each 2D heatmap of the tensor of 2D heatmaps exclusively representing possible positions for a corresponding single vertex of an individual triangle of a plurality of triangles of a three-dimensional (3D) mesh corresponding to the real-world object, the first machine learning model trained to predict a part of the 3D mesh that is not visible within the image including at least one of occluded vertices, self-occluded vertices, or truncated vertices, a first heatmap of the tensor of heatmaps representing a first group of possible coordinates exclusively for a single first vertex of a first triangle of the plurality of triangles, a second heatmap of the tensor of heatmaps representing a second group of possible coordinates exclusively for a single second vertex of the same first triangle as the first heatmap;

selecting a subset of the tensor of heatmaps from the tensor of heatmaps, the subset of the tensor of heatmaps comprising a first coordinate of the first group of possible coordinates and a second coordinate of the second group of possible coordinates; and

generating the 3D mesh based on the selected subset of the tensor of heatmaps, the 3D mesh being combined with an inpainted mesh to form a reconstructed 3D mesh.

19 . The system of claim 18 , the operations further comprising:

localizing vertices of the 3D mesh in two dimensions by applying a differentiable soft-argmax operation to the tensor of 2D heatmaps to obtain a two-dimensional (2D) position for each vertex.

20 . A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:

receiving an image that includes a depiction of a real-world object;

predicting a tensor of two-dimensional (2D) heatmaps by applying a first machine learning model to a portion of the image, each 2D heatmap of the tensor of 2D heatmaps exclusively representing possible positions for a corresponding single vertex of an individual triangle of a plurality of triangles of a three-dimensional (3D) mesh corresponding to the real-world object, the first machine learning model trained to predict a part of the 3D mesh that is not visible within the image including at least one of occluded vertices, self-occluded vertices, or truncated vertices, a first heatmap of the tensor of heatmaps representing a first group of possible coordinates exclusively for a single first vertex of a first triangle of the plurality of triangles, a second heatmap of the tensor of heatmaps representing a second group of possible coordinates exclusively for a single second vertex of the same first triangle as the first heatmap;

selecting a subset of the tensor of heatmaps from the tensor of heatmaps, the subset of the tensor of heatmaps comprising a first coordinate of the first group of possible coordinates and a second coordinate of the second group of possible coordinates; and

generating the 3D mesh based on the selected subset of the tensor of heatmaps, the 3D mesh being combined with an inpainted mesh to form a reconstructed 3D mesh.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 8, 2025
From: SNAP GROUP LIMITED
To: SNAP INC.
Reel/Frame 072510/0008 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 14, 2025
From: GULER, RIZA ALP; KAKOLYRIS, ANTONIOS; KOKKINOS, IASON; KOUTRAS, PETROS; LE, ERIC-TUAN; PAPANDREOU, GEORGIOS; SKORDOS, EFSTRATIOS; TAM, HIMMY
To: SNAP GROUP LIMITED
Reel/Frame 070512/0380 →
Priority Claims (1)
GR 20230100198 · Mar 8, 2023 · national
Continuity (1)
Related Publication 20240303937A1 · Sep 12, 2024
References Cited (336)
US 5604843A · Shaw et al. · 1997 [cited by applicant]
US 5689559A · Park · 1997 [cited by applicant]
US 5880731A · Liles et al. · 1999 [cited by applicant]
US 6023270A · Brush, II et al. · 2000 [cited by applicant]
US RE36919E · Park · 2000 [cited by applicant]
US RE37052E · Park · 2001 [cited by applicant]
US 6223165B1 · Lauffer · 2001 [cited by applicant]
US 6650793B1 · Lund et al. · 2003 [cited by applicant]
US 6772195B1 · Hatlelid et al. · 2004 [cited by applicant]
US 6804417B1 · Lund et al. · 2004 [cited by applicant]
US 6842779B1 · Nishizawa · 2005 [cited by applicant]
US 7342587B2 · Danzig et al. · 2008 [cited by applicant]
US 7468729B1 · Levinson · 2008 [cited by applicant]
US 7636755B2 · Blattner et al. · 2009 [cited by applicant]
US 7639251B2 · Gu et al. · 2009 [cited by applicant]
US 7775885B2 · Van Luchene et al. · 2010 [cited by applicant]
US 7859551B2 · Bulman et al. · 2010 [cited by applicant]
US 7885931B2 · Seo et al. · 2011 [cited by applicant]
US 7925703B2 · Dinan et al. · 2011 [cited by applicant]
US 8088044B2 · Tchao et al. · 2012 [cited by applicant]
US 8095878B2 · Bates et al. · 2012 [cited by applicant]
US 8108774B2 · Finn et al. · 2012 [cited by applicant]
US 8117281B2 · Robinson et al. · 2012 [cited by applicant]
US 8130219B2 · Fleury et al. · 2012 [cited by applicant]
US 8146005B2 · Jones et al. · 2012 [cited by applicant]
US 8151191B2 · Nicol · 2012 [cited by applicant]
US RE43993E · Park · 2013 [cited by applicant]
US 8384719B2 · Reville et al. · 2013 [cited by applicant]
US RE44054E · Kim · 2013 [cited by applicant]
US RE44068E · Park · 2013 [cited by applicant]
US RE44106E · Park · 2013 [cited by applicant]
US 8396708B2 · Park et al. · 2013 [cited by applicant]
US RE44121E · Park · 2013 [cited by applicant]
US 8425322B2 · Gillo et al. · 2013 [cited by applicant]
US 8458601B2 · Castelli et al. · 2013 [cited by applicant]
US 8462198B2 · Lin et al. · 2013 [cited by applicant]
US 8484158B2 · Deluca et al. · 2013 [cited by applicant]
US 8495503B2 · Brown et al. · 2013 [cited by applicant]
US 8495505B2 · Smith et al. · 2013 [cited by applicant]
US 8504926B2 · Wolf · 2013 [cited by applicant]
US 8559980B2 · Pujol · 2013 [cited by applicant]
US 8564621B2 · Branson et al. · 2013 [cited by applicant]
US 8564710B2 · Nonaka et al. · 2013 [cited by applicant]
US 8581911B2 · Becker et al. · 2013 [cited by applicant]
US 8597121B2 · del Valle · 2013 [cited by applicant]
US 8601051B2 · Wang · 2013 [cited by applicant]
US 8601379B2 · Marks et al. · 2013 [cited by applicant]
US 8632408B2 · Gillo et al. · 2014 [cited by applicant]
US 8648865B2 · Dawson et al. · 2014 [cited by applicant]
US 8659548B2 · Hildreth · 2014 [cited by applicant]
US 8683354B2 · Khandelwal et al. · 2014 [cited by applicant]
US 8692830B2 · Nelson et al. · 2014 [cited by applicant]
US 8810513B2 · Ptucha et al. · 2014 [cited by applicant]
US 8812171B2 · Filev et al. · 2014 [cited by applicant]
US 8832201B2 · Wall · 2014 [cited by applicant]
US 8832552B2 · Arrasvuori et al. · 2014 [cited by applicant]
US 8839327B2 · Amento et al. · 2014 [cited by applicant]
US 8890926B2 · Tandon et al. · 2014 [cited by applicant]
US 8892999B2 · Nims et al. · 2014 [cited by applicant]
US 8924250B2 · Bates et al. · 2014 [cited by applicant]
US 8963926B2 · Brown et al. · 2015 [cited by applicant]
US 8989786B2 · Feghali · 2015 [cited by applicant]
US 9086776B2 · Ye et al. · 2015 [cited by applicant]
US 9105014B2 · Collet et al. · 2015 [cited by applicant]
US 9241184B2 · Weerasinghe · 2016 [cited by applicant]
US 9256860B2 · Herger et al. · 2016 [cited by applicant]
US 9298257B2 · Hwang et al. · 2016 [cited by applicant]
US 9314692B2 · Konoplev et al. · 2016 [cited by applicant]
US 9330483B2 · Du et al. · 2016 [cited by applicant]
US 9357174B2 · Li et al. · 2016 [cited by applicant]
US 9361510B2 · Yao et al. · 2016 [cited by applicant]
US 9378576B2 · Bouaziz et al. · 2016 [cited by applicant]
US 9402057B2 · Kaytaz et al. · 2016 [cited by applicant]
US 9412192B2 · Mandel et al. · 2016 [cited by applicant]
US 9460541B2 · Li et al. · 2016 [cited by applicant]
US 9489760B2 · Li et al. · 2016 [cited by applicant]
US 9503845B2 · Vincent · 2016 [cited by applicant]
US 9508197B2 · Quinn et al. · 2016 [cited by applicant]
US 9532364B2 · Fujito · 2016 [cited by applicant]
US 9544257B2 · Ogundokun et al. · 2017 [cited by applicant]
US 9576400B2 · Van Os et al. · 2017 [cited by applicant]
US 9589357B2 · Li et al. · 2017 [cited by applicant]
US 9592449B2 · Barbalet et al. · 2017 [cited by applicant]
US 9648376B2 · Chang et al. · 2017 [cited by applicant]
US 9697635B2 · Quinn et al. · 2017 [cited by applicant]
US 9706040B2 · Kadirvel et al. · 2017 [cited by applicant]
US 9744466B2 · Fujioka · 2017 [cited by applicant]
US 9746990B2 · Anderson et al. · 2017 [cited by applicant]
US 9749270B2 · Collet et al. · 2017 [cited by applicant]
US 9792714B2 · Li et al. · 2017 [cited by applicant]
US 9839844B2 · Dunstan et al. · 2017 [cited by applicant]
US 9883838B2 · Kaleal, III et al. · 2018 [cited by applicant]
US 9898849B2 · Du et al. · 2018 [cited by applicant]
US 9911073B1 · Spiegel et al. · 2018 [cited by applicant]
US 9936165B2 · Li et al. · 2018 [cited by applicant]
US 9959037B2 · Chaudhri et al. · 2018 [cited by applicant]
US 9980100B1 · Charlton et al. · 2018 [cited by applicant]
US 9990373B2 · Fortkort · 2018 [cited by applicant]
US 10039988B2 · Lobb et al. · 2018 [cited by applicant]
US 10097492B2 · Tsuda et al. · 2018 [cited by applicant]
US 10116598B2 · Tucker et al. · 2018 [cited by applicant]
US 10155168B2 · Blackstock et al. · 2018 [cited by applicant]
US 10158589B2 · Collet et al. · 2018 [cited by applicant]
US 10242477B1 · Charlton et al. · 2019 [cited by applicant]
US 10242503B2 · McPhee et al. · 2019 [cited by applicant]
US 10262250B1 · Spiegel et al. · 2019 [cited by applicant]
US 10348662B2 · Baldwin et al. · 2019 [cited by applicant]
US 10362219B2 · Wilson et al. · 2019 [cited by applicant]
US 10432559B2 · Baldwin et al. · 2019 [cited by applicant]
US 10454857B1 · Blackstock et al. · 2019 [cited by applicant]
US 10475225B2 · Park et al. · 2019 [cited by applicant]
US 10504266B2 · Blattner et al. · 2019 [cited by applicant]
US 10573048B2 · Ni et al. · 2020 [cited by applicant]
US 10656797B1 · Alvi et al. · 2020 [cited by applicant]
US 10657695B2 · Chand et al. · 2020 [cited by applicant]
US 10657701B2 · Osman et al. · 2020 [cited by applicant]
US 10762174B2 · Denton et al. · 2020 [cited by applicant]
US 10805248B2 · Luo et al. · 2020 [cited by applicant]
US 10872451B2 · Sheth et al. · 2020 [cited by applicant]
US 10880246B2 · Baldwin et al. · 2020 [cited by applicant]
US 10895964B1 · Grantham et al. · 2021 [cited by applicant]
US 10896534B1 · Smith et al. · 2021 [cited by applicant]
US 10933311B2 · Brody et al. · 2021 [cited by applicant]
US 10938758B2 · Allen et al. · 2021 [cited by applicant]
US 10964082B2 · Amitay et al. · 2021 [cited by applicant]
US 10979752B1 · Brody et al. · 2021 [cited by applicant]
US 10984575B2 · Assouline et al. · 2021 [cited by applicant]
US 10992619B2 · Antmen et al. · 2021 [cited by applicant]
US 11010022B2 · Alvi et al. · 2021 [cited by applicant]
US 11030789B2 · Chand et al. · 2021 [cited by applicant]
US 11036781B1 · Baril et al. · 2021 [cited by applicant]
US 11063891B2 · Voss · 2021 [cited by applicant]
US 11069103B1 · Blackstock et al. · 2021 [cited by applicant]
US 11080917B2 · Monroy-hernández et al. · 2021 [cited by applicant]
US 11128586B2 · Al Majid et al. · 2021 [cited by applicant]
US 11188190B2 · Blackstock et al. · 2021 [cited by applicant]
US 11189070B2 · Jahangiri et al. · 2021 [cited by applicant]
US 11199957B1 · Alvi et al. · 2021 [cited by applicant]
US 11218433B2 · Baldwin et al. · 2022 [cited by applicant]
US 11229849B2 · Blackstock et al. · 2022 [cited by applicant]
US 11245658B2 · Grantham et al. · 2022 [cited by applicant]
US 11249614B2 · Brody · 2022 [cited by applicant]
US 11263254B2 · Baril et al. · 2022 [cited by applicant]
US 11270491B2 · Monroy-Hernández et al. · 2022 [cited by applicant]
US 11284144B2 · Kotsopoulos et al. · 2022 [cited by applicant]
US 20020067362A1 · Agostino Nocera et al. · 2002 [cited by applicant]
US 20020169644A1 · Greene · 2002 [cited by applicant]
US 20050162419A1 · Kim et al. · 2005 [cited by applicant]
US 20050206610A1 · Cordelli · 2005 [cited by applicant]
US 20060294465A1 · Ronen et al. · 2006 [cited by applicant]
US 20070113181A1 · Blattner et al. · 2007 [cited by applicant]
US 20070168863A1 · Blattner et al. · 2007 [cited by applicant]
US 20070176921A1 · Iwasaki et al. · 2007 [cited by applicant]
US 20080158222A1 · Li et al. · 2008 [cited by applicant]
US 20090016617A1 · Bregman-Amitai et al. · 2009 [cited by applicant]
US 20090055484A1 · Vuong et al. · 2009 [cited by applicant]
US 20090070688A1 · Gyorfi et al. · 2009 [cited by applicant]
US 20090099925A1 · Mehta et al. · 2009 [cited by applicant]
US 20090106672A1 · Burstrom · 2009 [cited by applicant]
US 20090158170A1 · Narayanan et al. · 2009 [cited by applicant]
US 20090177976A1 · Bokor et al. · 2009 [cited by applicant]
US 20090202114A1 · Morin et al. · 2009 [cited by applicant]
US 20090265604A1 · Howard et al. · 2009 [cited by applicant]
US 20090300525A1 · Jolliff et al. · 2009 [cited by applicant]
US 20090303984A1 · Clark et al. · 2009 [cited by applicant]
US 20100011422A1 · Mason et al. · 2010 [cited by applicant]
US 20100023885A1 · Reville et al. · 2010 [cited by applicant]
US 20100115426A1 · Liu et al. · 2010 [cited by applicant]
US 20100162149A1 · Sheleheda et al. · 2010 [cited by applicant]
US 20100203968A1 · Gill et al. · 2010 [cited by applicant]
US 20100227682A1 · Reville et al. · 2010 [cited by applicant]
US 20110093780A1 · Dunn · 2011 [cited by applicant]
US 20110115798A1 · Nayar et al. · 2011 [cited by applicant]
US 20110148864A1 · Lee et al. · 2011 [cited by applicant]
US 20110239136A1 · Goldman et al. · 2011 [cited by applicant]
US 20120113106A1 · Choi et al. · 2012 [cited by applicant]
US 20120124458A1 · Cruzada · 2012 [cited by applicant]
US 20120130717A1 · Xu et al. · 2012 [cited by applicant]
US 20130103760A1 · Golding et al. · 2013 [cited by applicant]
US 20130201187A1 · Tong et al. · 2013 [cited by applicant]
US 20130249948A1 · Reitan · 2013 [cited by applicant]
US 20130257877A1 · Davis · 2013 [cited by applicant]
US 20140043329A1 · Wang et al. · 2014 [cited by applicant]
US 20140055554A1 · Du et al. · 2014 [cited by applicant]
US 20140125678A1 · Wang et al. · 2014 [cited by applicant]
US 20140129343A1 · Finster et al. · 2014 [cited by applicant]
US 20150206349A1 · Rosenthal et al. · 2015 [cited by applicant]
US 20160134840A1 · Mcculloch · 2016 [cited by applicant]
US 20160234149A1 · Tsuda et al. · 2016 [cited by applicant]
US 20170080346A1 · Abbas · 2017 [cited by applicant]
US 20170087473A1 · Siegel et al. · 2017 [cited by applicant]
US 20170113140A1 · Blackstock et al. · 2017 [cited by applicant]
US 20170118145A1 · Aittoniemi et al. · 2017 [cited by applicant]
US 20170199855A1 · Fishbeck · 2017 [cited by applicant]
US 20170235848A1 · Van Deusen et al. · 2017 [cited by applicant]
US 20170310934A1 · Du et al. · 2017 [cited by applicant]
US 20170312634A1 · Ledoux et al. · 2017 [cited by applicant]
US 20180047200A1 · O'hara et al. · 2018 [cited by applicant]
US 20180113587A1 · Allen et al. · 2018 [cited by applicant]
US 20180115503A1 · Baldwin et al. · 2018 [cited by applicant]
US 20180198743A1 · Blackstock et al. · 2018 [cited by applicant]
US 20180315076A1 · Andreou · 2018 [cited by applicant]
US 20180315133A1 · Brody et al. · 2018 [cited by applicant]
US 20180315134A1 · Amitay et al. · 2018 [cited by applicant]
US 20190001223A1 · Blackstock et al. · 2019 [cited by applicant]
US 20190057616A1 · Cohen et al. · 2019 [cited by applicant]
US 20190097958A1 · Collet et al. · 2019 [cited by applicant]
US 20190188920A1 · Mcphee et al. · 2019 [cited by applicant]
US 20190280997A1 · Baldwin et al. · 2019 [cited by applicant]
US 20200306637A1 · Baldwin et al. · 2020 [cited by applicant]
US 20200372127A1 · Denton et al. · 2020 [cited by applicant]
US 20200410575A1 · Grantham et al. · 2020 [cited by applicant]
US 20210074047A1 · Sheth et al. · 2021 [cited by applicant]
US 20210089179A1 · Grantham et al. · 2021 [cited by applicant]
US 20210104087A1 · Smith et al. · 2021 [cited by applicant]
US 20210168108A1 · Antmen et al. · 2021 [cited by applicant]
US 20210170270A1 · Brody et al. · 2021 [cited by applicant]
US 20210192823A1 · Amitay et al. · 2021 [cited by applicant]
US 20210209825A1 · Assouline et al. · 2021 [cited by applicant]
US 20210225058A1 · Chand et al. · 2021 [cited by applicant]
US 20210240315A1 · Alvi et al. · 2021 [cited by applicant]
US 20210243482A1 · Baril et al. · 2021 [cited by applicant]
US 20210243503A1 · Kotsopoulos et al. · 2021 [cited by applicant]
US 20210256776A1 · Cappello · 2021 [cited by examiner]
US 20210266277A1 · Allen et al. · 2021 [cited by applicant]
US 20210281897A1 · Brody et al. · 2021 [cited by applicant]
US 20210285774A1 · Collins et al. · 2021 [cited by applicant]
US 20210306290A1 · Voss · 2021 [cited by applicant]
US 20210306451A1 · Heikkinen et al. · 2021 [cited by applicant]
US 20210385180A1 · Al Majid et al. · 2021 [cited by applicant]
US 20210405831A1 · Mourkogiannis et al. · 2021 [cited by applicant]
US 20210409535A1 · Mourkogiannis et al. · 2021 [cited by applicant]
US 20220012929A1 · Blackstock et al. · 2022 [cited by applicant]
US 20230077856A1 · Irshad · 2023 [cited by examiner]
US 20240046566A1 · Yang · 2024 [cited by examiner]
CN 109863532A · 2019 [cited by applicant]
CN 110168478A · 2019 [cited by applicant]
CN 113012282A · 2021 [cited by examiner]
EP 2184092A2 · 2010 [cited by applicant]
JP 2001230801A · 2001 [cited by applicant]
JP 5497931B2 · 2014 [cited by applicant]
KR 101445263B1 · 2014 [cited by applicant]
WO WO2003094072A1 · 2003 [cited by applicant]
WO WO2004095308A1 · 2004 [cited by applicant]
WO WO2006107182A1 · 2006 [cited by applicant]
WO WO2007134402A1 · 2007 [cited by applicant]
WO WO2012139276A1 · 2012 [cited by applicant]
WO WO2013027893A1 · 2013 [cited by applicant]
WO WO2013152454A1 · 2013 [cited by applicant]
WO WO2013166588A1 · 2013 [cited by applicant]
WO WO2014031899A1 · 2014 [cited by applicant]
WO WO2014194439A1 · 2014 [cited by applicant]
WO WO2016090605A1 · 2016 [cited by applicant]
WO WO2018081013A1 · 2018 [cited by applicant]
WO WO2018102562A1 · 2018 [cited by applicant]
WO WO2018129531A1 · 2018 [cited by applicant]
WO WO2019089613A1 · 2019 [cited by applicant]
Moon et al., “Camera Distance-Aware Top-Down Approach for 3D Multi-Person Pose Estimation From a Single RGB Image,” 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 10132-10141. (Year: 2019). [cited by examiner]
Feng et al., “TerrainMesh: Metric-Semantic Terrain Reconstruction from Aerial Images Using Joint 2D-3D Learning,” arXiv: 2204.10993, 2022. (Year: 2022). [cited by examiner]
Kocabas et al., “PARE: Part Attention Regressor for 3D Human Body Estimation”, Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 11127-11137, 2021. (Year: 2021). [cited by examiner]
“Bitmoji”, Snapchat Support, [Online] Retrieved from the Internet: <URL: https://web.archive.org/web/20190503063620/https://support.snapchat.com/en-US/a/bitmoji>, (captured May 3, 2019), 2 pgs. [cited by applicant]
“Bitmoji Chrome Extension”, [Online] Retrieved from the Internet: <URL: https://web.archive.org/web/20200919024925/https://support.bimoji.com/hc/en-us/articles/360001494066>, (Sep. 19, 2020), 5 pgs. [cited by applicant]
“Bitmoji Customize text”, [Online] Retrieved from the Internet: <URL: https://web.archive.org/web/20210225200456/https://support.bitmoji.com/hc/en-us/articles/360034632291-Customize-Text-on-Bitmoji-Stickers>, (captured … [cited by applicant]
“Bitmoji Family”, Snapchat Support, [Online] Retrieved from the Internet: <URL: https://web.archive.org/web/20190503063620/https://support.snapchat.com/en-US/article/bitmoji-family>, (captured May 3, 2019), 4 pgs. [cited by applicant]
“Instant Comics Starring You & Your Friends”, Bitstrips Inc, [Online] Retrieved from the Internet: <URL: https://web.archive.org/web/20150206000940/http://company.bitstrips.com/bitstrips-app.html>, (captured Feb. 6, 201… [cited by applicant]
“Manage Your Bitmoji”, Snapchat Support, [Online] Retrieved from the Internet: <URL: https://web.archive.org/web/20190503063620/https://support.snapchat.com/en-US/a/manage-bitmoji>, (captured May 3, 2019), 3 pgs. [cited by applicant]
“Your Own Personal Emoji”, Bitstrips Inc, [Online] Retrieved from the Internet: <URL: https://web.archive.org/web/20150205232004/http://bitmoji.com/>, (captured Feb. 5, 2015), 3 pgs. [cited by applicant]
Carnahan, Daniel, “Snap is Offering Personalized Video Content Through Bitmoji TV”, Business Insider, [Online] Retrieved from the Internet: <URL: https://www.businessinsider.com/snap-offers-personalized-video-content-th… [cited by applicant]
Constine, Josh, “Snapchat launches Bitmoji merch and comic strips starring your avatar”, TechCrunch, [Online] Retrieved from the Internet: <URL: https://techcrunch.com/2018/11/13/bitmoji-store/>, (Nov. 13, 2018), 16 pgs. [cited by applicant]
Constine, Josh, “Snapchat Launches Bitmoji TV: Zany 4-min Cartoons of Your Avatar”, TechCrunch, [Online] Retrieved from the Internet: <URL: https://techcrunch.com/2020/01/30/bitmoji-tv/>, (Jan. 30, 2020), 13 pgs. [cited by applicant]
Macmillan, Douglas, “Snapchat Buys Bitmoji App for More Than $100 Million”, The Wallstreet Journal, [Online] Retrieved from the Internet: <URL: https://www.wsj.com/articles/snapchat-buys-bitmoji-app-for-more-than-100-mi… [cited by applicant]
Newton, Casey, “Your Snapchat friendships now have their own profiles—and merchandise”, The Verge, [Online] Retrieved from the Internet: <URL: https://www.theverge.com/2018/11/13/18088772/snapchat-friendship-profiles-bi… [cited by applicant]
Ong, Thuy, “Snapchat takes Bitmoji deluxe with hundreds of new customization options”, The Verge, [Online] Retrieved from the Internet on Nov. 2, 2018: <URL: https://www.theverge.com/2018/1/30/16949402/bitmoji-deluxe-sn… [cited by applicant]
Reign, Ashley, “How To Add My Friend's Bitmoji To My Snapchat”, Women.com, [Online] Retrieved from the Internet: <URL: https://www.women.com/ashleyreign/lists/how-to-add-my-friends-bitmoji-to-my-snapchat>, (Jun. 30, 201… [cited by applicant]
Tumbokon, Karen, “Snapchat Update: How To Add Bitmoji To Customizable Geofilters”, International Business Times, [Online] Retrieved from the Internet : <URL: https://www.ibtimes.com/snapchat-update-how-add-bitmoji-custo… [cited by applicant]
“International Application Serial No. PCT/US2024/018883, International Search Report mailed Jun. 20, 2024”, 2 pgs. [cited by applicant]
“International Application Serial No. PCT/US2024/018883, Written Opinion mailed Jun. 20, 2024 (24”, 9 pgs. [cited by applicant]
Guler, Riza Alp, et al., “DensePose: Dense Human Pose Estimation in the Wild”, IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, (Jun. 18, 2018), 10 pgs. [cited by applicant]
Moon, Gyeongsik, et al., “12L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image”, (Nov. 9, 2020), 17 pgs. [cited by applicant]
“Core ML”, Apple Developer Documentation, [Online]. Retrieved from the Internet: <URL: https://web.archive.org/web/20220615172550/https://developer.apple.com/documentation/coreml>, (archived Jun. 15, 2022), 3 pgs. [cited by applicant]
“TensorFlow Lite”, [Online]. Retrieved from the Internet: <URL: https://web.archive.org/web/20221121085048/https://www.tensorflow.org/lite/guide>, (archived Nov. 21, 2022), 5 pgs. [cited by applicant]
Albahar, Badour, et al., “Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN”, arxiv.org, Cornell University Library, 201 Olin Library Cornell University Ithaca, NY 14853, (Sep. 13,… [cited by applicant]
Cho, Junhyeong, et al., “Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers”, arXiv preprint arXiv:2207.13820v1, (Jul. 27, 2022), 22 pgs. [cited by applicant]
Choi, Hongsuk, et al., “Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2021), 10 pgs. [cited by applicant]
Choi, Hongsuk, et al., “Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose”, ECCV, (2020), 20 pgs. [cited by applicant]
Corona, Enric, et al., “Learned Vertex Descent: A New Direction for 3D Human Model Fitting”, arXiv preprint arXiv:2205.06254v2, (Jul. 19, 2022), 27 pgs. [cited by applicant]
Du, Chengdu, et al., “Greatness in Simplicity: Unified Self-Cycle Consistency for Parser-Free Virtual Try-On”, Advances in Neural Information Processing Systems, 36, (2023), 12 pgs. [cited by applicant]
Goel, Shubham, et al., “Humans in 4D: Reconstructing and Tracking Humans with Transformers”, Proceedings of the IEEE/CVF International Conference on Computer Vision, (2023), 14783-14794. [cited by applicant]
Guler, Riza Alp, et al., “DensePose: Dense Human Pose Estimation In The Wild”, IEEE/CVF Conference on Computer Vision and Pattern Recognition, [Online] Retrieved from the internet: <URL: https://arxiv.org/pdf/1802.00434… [cited by applicant]
Guler, Riza Alp, et al., “HoloPose: Holistic 3D Human Reconstruction In-The-Wild”, CVPR, (Jun. 20, 2019), 11 pgs. [cited by applicant]
Hassan, Mohamed, et al., “Resolving 3D Human Pose Ambiguities with 3D Scene Constraints”, Proceedings of the IEEE/CVF International Conference on Computer Vision, (2019), 2282-2292. [cited by applicant]
He, Kaiming, et al., “Deep Residual Learning for Image Recognition”, IEEE Conference on Computer Vision and Pattern Recognition, (2016), 770-778. [cited by applicant]
Ionescu, Catalin, et al., “Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, No. 7, pp. 1325-1… [cited by applicant]
Iqbal, Umar, et al., “KAMA: 3D Keypoint Aware Body Mesh Articulation”, arXiv preprint arXiv:2104.13502v1, (Apr. 27, 2021), 11 pgs. [cited by applicant]
Jiang, Wen, et al., “Coherent Reconstruction of Multiple Humans from a Single Image”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2020), 82-91. [cited by applicant]
Joo, Hanbyul, et al., “Exemplar Fine-Tuning for 3D Human Pose Fitting Towards In-the-Wild 3D Human Pose Estimation”, arXiv preprint arXiv:2004.03686v1, (Apr. 7, 2020), 10 pgs. [cited by applicant]
Kanazawa, Angjoo, et al., “End-to-End Recovery of Human Shape and Pose”, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) IEEE Computer Society, (Jun. 18, 2018), 10 pgs. [cited by applicant]
Kervadec, Hoel, et al., “Boundary loss for highly unbalanced segmentation”, Proceedings of Machine Learning Research 102, (2019), 285-296. [cited by applicant]
Khirodkar, Rawal, et al., “Occluded Human Mesh Recovery”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (Jun. 2022), 1715-1725. [cited by applicant]
Kim, Jeonghwan, et al., “Sampling is Matter: Point-guided 3D Human Mesh Reconstruction”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (12880-12889), 2023. [cited by applicant]
Kocabas, Muhammed, et al., “PARE: Part Attention Regressor for 3D Human Body Estimation”, Proceedings of the IEEE/CVF International Conference on Computer Vision, (2021), 11127-11137. [cited by applicant]
Kocabas, Muhammed, et al., “SPEC: Seeing People in the Wild with an Estimated Camera”, Proceedings of the IEEE/CVF International Conference on Computer Vision, (2021), 11035-11045. [cited by applicant]
Kocabas, Muhammed, et al., “VIBE: Video Inference for Human Body Pose and Shape Estimation”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2020), 5253-5263. [cited by applicant]
Kolotouros, Nikos, et al., “Convolutional Mesh Regression for Single-Image Human Shape Reconstruction”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2019), 4501-4510. [cited by applicant]
Kolotouros, Nikos, “Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop”, Proceedings of the IEEE/CVF International Conference on Computer Vision, (2019), 2252-2261. [cited by applicant]
Kolotouros, Nikos, et al., “Probabilistic Modeling for Human Mesh Recovery”, Proceedings of the IEEE/CVF International Conference on Computer Vision, (2021), 11605-11614. [cited by applicant]
Li, Jiefeng, et al., “HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2021), 33… [cited by applicant]
Li, Jiefeng, et al., “NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2023), 1… [cited by applicant]
Li, Zhihao, et al., “CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation”, European Conference on Computer Vision (ECCV), (2022), 17 pgs. [cited by applicant]
Lin, Kevin, et al., “End-to-End Human Pose and Mesh Reconstruction with Transformers”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2021), 1954-1963. [cited by applicant]
Lin, Kevin, et al., “Mesh Graphormer”, Proceedings of the IEEE/CVF International Conference on Computer Vision, (2021), 12939-12948. [cited by applicant]
Lin, Tsung-Yi, et al., “Microsoft COCO: Common Objects in Context”, Computer Vision—ECCV 2014:13th European Conference, Zurich, Switzerland, Sep. 6-12, 2014, Proceedings, Part V 13, pp. 740-755, Springer, (2014), 15 pgs. [cited by applicant]
Ma, Xiaoxuan, et al., “3D Human Mesh Estimation from Virtual Markers”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2023), 534-543. [cited by applicant]
Mehta, Dushyant, et al., “Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision”, arXiv preprint arXiv:1611.09813v5, (Oct. 4, 2017), 16 pgs. [cited by applicant]
Moon, Gyeongsik, et al., “I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image”, arXiv:2008.03713v2 [cs.CV], (Nov. 1, 2020), 23 pgs. [cited by applicant]
Moon, Gyeongsik, et al., “NeuralAnnot: Neural Annotator for 3D Human Mesh Training Sets”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2022), 2299-2307. [cited by applicant]
Muller, Lea, et al., “On Self-Contact and Human Pose”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2021), 10 pgs. [cited by applicant]
Pavlakos, Georgios, et al., “Expressive Body Capture: 3D Hands, Face, and Body From a Single Image”, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019), 22 pgs. [cited by applicant]
Pavlakos, Georgios, et al., “Learning to Estimate 3D Human Pose and Shape from a Single Color Image”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2018), 459-468. [cited by applicant]
Sandler, Mark, et al., “MobileNetV2: Inverted Residuals and Linear Bottlenecks”, arXiv preprint arXiv:1801.04381v4 [cs.CV], (Mar. 21, 2019), 14 pgs. [cited by applicant]
Sarkar, Kripasindhu, “Style and Pose Control for Image Synthesis of Humans from a Single Monocular View”, [Online] Retrieved from the internet: <https://arxiv.Org/pdf/2102.11263>, (Feb. 22, 2021), 15 pgs. [cited by applicant]
Shetty, Karthik, et al., “Pliks: A pseudo-linear inverse kinematic solver for 3d human body estimation”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2023), 574-584. [cited by applicant]
Song, Jie, et al., “Human Body Model Fitting by Learned Gradient Descent”, ECCV, (2020), 17 pgs. [cited by applicant]
Sun, Yu, et al., “Monocular, One-stage, Regression of Multiple 3D People”, Proceedings of the IEEE/CVF International Conference on Computer Vision, (2021), 11179-11188. [cited by applicant]
Sun, Yu, et al., “Putting people in their place: Monocular regression of 3d people in depth”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2022), 13243-13252. [cited by applicant]
Von Marcard, Timo, et al., “Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving Camera”, Proceedings of the European Conference on Computer Vision (ECCV), (2018), 17 pgs. [cited by applicant]
Wang, Jingdong, et al., “Deep High-Resolution Representation Learning for Visual Recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, (Mar. 2020), 23 pgs. [cited by applicant]
Wang, Wenjia, et al., “Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction”, Proceedings of the IEEE/CVF International Conference on Computer Vision, (2023), 3925-3935. [cited by applicant]
Wang, Yufu, et al., “ReFit: Recurrent Fitting Network for 3D Human Recovery”, Proceedings of the IEEE/CVF International Conference on Computer Vision, (2023), 14644-14654. [cited by applicant]
Xiao, Bin, et al., “Simple Baselines for Human Pose Estimation and Tracking”, Proceedings of the European Conference on Computer Vision (ECCV), (2018), 16 pgs. [cited by applicant]
Xu, Hongyi, et al., “GHUM & GHUML: Generative 3D Human Shape and Articulated Pose Models”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2020), 6184-6193. [cited by applicant]
Yao, Chun-Han, et al., “Learning Visibility for Robust Dense Human Body Estimation”, European Conference on Computer Vision (ECCV), (2022), 17 pgs. [cited by applicant]
Zanfir, Andrei, et al., “Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows”, European Conference on Computer Vision (ECCV), Springer, (2020), 17 pgs. [cited by applicant]
Zhang, Hongwen, et al., “Learning 3D Human Shape and Pose From Dense Body Parts”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, Issue 5, (May 1, 2022), 2610-2627. [cited by applicant]
Zhang, Hongwen, et al., “PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop”, Proceedings of the IEEE/CVF International Conference on Computer Vision, (2021), 11446-11456. [cited by applicant]
Zhang, Tianshu, et al., “Object-Occluded Human Shape and Pose Estimation from a Single Color Image”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2020), 7376-7385. [cited by applicant]