IP Library › Granted Patent US 12,561,949
Granted Patent B2
US 12,561,949 · App. 18/329,385 · Granted Feb 24, 2026

Conditional procedural model generation

Inventors: Valentin Mathieu Deschaintre (London, GB); Yiwei Hu (New Haven, CT); Paul Guerrero (London, GB); Milos Hasan (Lafayette, CA)
Assignee: Adobe Inc.
G06V10/761G06V10/44G06V10/54
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 12,561,949
App. No.
18/329,385
Granted
Feb 24, 2026
Kind
B2
Abstract

Conditional procedural model generation techniques are described that enable generation of procedural models that are usable to recreate a visual appearance of an input image. A content processing system, for instance, receives a training dataset that includes a plurality of training pairs. The content processing system trains a machine learning model to generate procedural models based on input images. The content processing system then receives an input image that has a particular visual appearance. The content processing system leverages the trained machine learning model to generate a procedural model that is usable to recreate the particular visual appearance of the input digital image.

Claims (34)

1 . A method comprising:

receiving, by a processing device, a training dataset including a plurality of training pairs, each said training pair including a training procedural model and a corresponding training target image;

configuring, by the processing device, a machine learning model to generate procedural models based on input digital images by training a conditional node transformer, a conditional edge transformer, and a conditional parameter transformer of the machine learning model using the training dataset;

receiving, by the processing device, an input including an input digital image having a particular visual appearance; and

generating, by the processing device, a procedural model usable to recreate the particular visual appearance of the input digital image using the trained machine learning model.

2 . The method as described in claim 1 , wherein the procedural model is a node graph that includes a sequence of parametrized nodes connected by one or more edges to represent one or more of a digital texture or a digital pattern of the input digital image.

3 . The method as described in claim 1 , further comprising generating the training dataset, wherein the generating the training dataset includes removing at least one switch node from one or more training procedural models, and sampling a plurality of parameter sets for each said training pair.

4 . The method as described in claim 1 , wherein the configuring the machine learning model includes calculating a binary cross-entropy loss over probabilities generated by the conditional node transformer, the conditional edge transformer, and the conditional parameter transformer.

5 . The method as described in claim 1 , wherein the generating the procedural model includes encoding the input digital image into a feature vector and conditioning the conditional node transformer, the conditional edge transformer, and the conditional parameter transformer on the feature vector.

6 . The method as described in claim 5 , wherein the conditional parameter transformer is conditioned on the feature vector, node sequences generated by the conditional node transformer, and edge sequences generated by the conditional node transformer.

7 . The method as described in claim 1 , wherein the generating the procedural model includes generating candidate procedural models, generating a ranking for each of the candidate procedural models based on a visual similarity of candidate digital images based on the candidate procedural models to the input digital image, and generating the procedural model based on the ranking.

8 . The method as described in claim 7 , wherein the ranking is based on one or more of a sliced Wasserstein distance or a CLIP cosine distance between the candidate digital images and the input digital image.

9 . The method as described in claim 1 , wherein the generating the procedural model includes generating a node sequence based on the input digital image by the conditional node transformer, generating an edge sequence based on the input digital image and the node sequence using the conditional edge transformer, and generating a parameter sequence based on the input digital image, the node sequence, and the edge sequence using the conditional parameter transformer.

10 . A system comprising:

a memory component; and

a processing device coupled to the memory component, the processing device to perform operations including:

receiving a trained machine learning model configured to generate procedural models based on input digital images;

receiving an input including an input digital image having a particular visual appearance; and

generating a procedural model usable to recreate the particular visual appearance of the input digital image by conditioning a conditional node transformer, a conditional edge transformer, and a conditional parameter transformer of the trained machine learning model on visual features of the input digital image.

11 . The system as described in claim 10 , wherein the procedural model is a node graph that represents one or more of a digital texture, a digital pattern, or a digital material of the input digital image.

12 . The system as described in claim 10 , wherein the trained machine learning model is trained by independently training the conditional node transformer, the conditional edge transformer, and the conditional parameter transformer.

13 . The system as described in claim 12 , wherein the trained machine learning model is trained by calculating a binary cross-entropy loss over probabilities generated by the trained machine learning model during training.

14 . The system as described in claim 10 , wherein the generating the procedural model includes generating a plurality of candidate procedural models, generating a ranking for each of the candidate procedural models based on a visual similarity of candidate digital images based on the candidate procedural models to the input digital image, and generating the procedural model based on the ranking.

15 . The system as described in claim 10 , wherein the generating the procedural model includes performing one or more semantic validity checks.

16 . The system as described in claim 10 , wherein generating the procedural model includes generating nodes for the procedural model using the conditional node transformer, generating edges between the nodes using the conditional edge transformer, and generating parameters for each of the nodes using the conditional parameter transformer.

17 . A non-transitory computer-readable storage medium storing executable instructions, which when executed by a processing device, cause the processing device to perform operations comprising:

training a node transformer, an edge transformer, and a parameter transformer of a machine learning model configured to generate procedural models;

receiving, in a user interface of the processing device, an input to initiate generation of a procedural model;

generating, responsive to the input, a node sequence using the node transformer and an edge sequence using the edge transformer of the machine learning model;

generating a parameter sequence using the parameter transformer based on the node sequence and the edge sequence; and

generating the procedural model based on the node sequence, the edge sequence, and the parameter sequence.

18 . The non-transitory computer-readable storage medium as described in claim 17 , further comprising generating a set of procedural models that includes a plurality of procedural models that represent a plurality of digital textures, digital materials, and digital patterns.

19 . The non-transitory computer-readable storage medium as described in claim 17 , wherein the edge sequence is based on the node sequence.

20 . The non-transitory computer-readable storage medium as described in claim 17 , wherein the training includes independently training the node transformer, the edge transformer, and the parameter transformer.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 5, 2023
From: DESCHAINTRE, VALENTIN MATHIEU; HU, YIWEI; GUERRERO, PAUL; HASAN, MILOS
To: ADOBE INC.
Reel/Frame 063857/0908 →
Continuity (1)
Related Publication 20240404244A1 · Dec 5, 2024
References Cited (91)
US 10134108B2 · Amirghodsi et al. · 2018 [cited by applicant]
US 10636209B1 · Thaller et al. · 2020 [cited by applicant]
US 11410361B2 · Krs · 2022 [cited by examiner]
US 11900514B2 · Krs et al. · 2024 [cited by applicant]
US 20130120392A1 · Mech · 2013 [cited by examiner]
US 20140369670A1 · Herfet et al. · 2014 [cited by applicant]
US 20150084989A1 · Laughlin et al. · 2015 [cited by applicant]
US 20160048636A1 · Warner et al. · 2016 [cited by applicant]
US 20170278289A1 · Marino et al. · 2017 [cited by applicant]
US 20180101972A1 · Asente et al. · 2018 [cited by applicant]
US 20190287224A1 · Amirghodsi et al. · 2019 [cited by applicant]
US 20200285464A1 · Brebner · 2020 [cited by applicant]
US 20220130086A1 · Krs et al. · 2022 [cited by applicant]
US 20220179374A1 · Kaberg Johard · 2022 [cited by applicant]
US 20220351436A1 · Krs et al. · 2022 [cited by applicant]
Node Grapg Optimization Using Differentiable Proxies, Yiwei Hu et al., arXiv, 2022, pp. 1-9 (Year: 2022). [cited by examiner]
A Novel Framework For Inverse Procedural Texture Modeling, Yiwei Hu et al., ACM, 2019, pp. 186:1 to 186:14 (Year: 2019). [cited by examiner]
A Sliced Wasserstein Loss for Neural Texture Synthesis, Eric Heitz et al., arXiv, 2021, pp. 1-9 (Year: 2021). [cited by examiner]
MatFormer: A Generative Model for Procedural Materials, Paul Guerrero et al., arXiv, 2022, pp. 46:1-46:12 (Year: 2022). [cited by examiner]
Node Graph Optimization Using Differentiable Proxies, Yiwei Hu et al., arXiv, 2022, pp. 1-9 (Year: 2022). [cited by examiner]
Flexible SVBRDF Capture with a Multi-Image Deep Network, Valentin Deschaintre et al., arXiv, 2019, pp. 1-14 (Year: 2019). [cited by examiner]
Image Transformer, Niki Parmar et al., PMLR, 2018, pp. 1-10 (Year: 2018). [cited by examiner]
U.S. Appl. No. 17/867,082, “Notice of Allowance”, U.S. Appl. No. 17/867,082, Oct. 16, 2023, 8 pages. [cited by applicant]
“Adobe Substance 3D”, Adobe [retrieved Mar. 24, 2023]. Retrieved from the Internet <https://www.substance3d.com/>., 2 Pages. [cited by applicant]
“Final Office Action”, U.S. Appl. No. 17/079,915, Dec. 29, 2021, 16 pages. [cited by applicant]
“First Action Interview Office Action”, U.S. Appl. No. 17/079,915, Nov. 16, 2021, 3 pages. [cited by applicant]
“Notice of Allowance”, U.S. Appl. No. 17/079,915, Mar. 30, 2022, 9 pages. [cited by applicant]
“Pre-Interview First Office Action”, U.S. Appl. No. 17/079,915, Oct. 21, 2021, 3 pages. [cited by applicant]
U.S. Appl. No. 17/867,082, “Final Office Action”, U.S. Appl. No. 17/867,082, May 11, 2023, 29 pages. [cited by applicant]
U.S. Appl. No. 17/867,082, “Non-Final Office Action”, U.S. Appl. No. 17/867,082, Nov. 25, 2022, 24 pages. [cited by applicant]
U.S. Appl. No. 17/867,082, “Non-Final Office Action”, U.S. Appl. No. 17/867,082, Jul. 20, 2023, 33 pages. [cited by applicant]
Aggarwal, Pranav et al., “Controlled and Conditional Text to Image Generation using Diffusion PriOR”, Cornell University arXiv, arXiv.org [retrieved Apr. 3, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2302… [cited by applicant]
Alhashim, Ibraheem et al., “Deformation-Driven Topology-Varying 3D Shape Correspondence”, ACM Transactions on Graphics, vol. 34, Issue 6, 2015 [retrieved on Oct. 2, 2020]. Retrieved from the Internet <shorturl.at/buGRS>… [cited by applicant]
Aristidou, A et al., “Inverse Kinematics Techniques in Computer Graphics: A Survey”, Wiley Online Linrary, Computer Graphics Forum, vol. 37, Issue 6 [retrieved on Oct. 2, 2020]. Retrieved from the Internet <shorturl.at/… [cited by applicant]
Beneš, B. et al., “Guided Procedural Modeling”, Computer Graphics Forum, vol. 30, No. 2 [retrieved Oct. 21, 2021]. Retrieved from the Internet <https://doi.org/10.1111/j.1467-8659.2011.01886.x>., Apr. 28, 2011, 10 pages. [cited by applicant]
Brown, Tom et al., “Language Models are Few-Shot Learners”, Advances in Neural Information Processing Systems [retrieved Mar. 27, 2023]. Retrieved from the Internet <https://armatech.us/OpenLanding/Language%20Models%20a… [cited by applicant]
Cook, Robert L. et al., “A Reflectance Model for Computer Graphics”, ACM Transactions on Graphics [retrieved Mar. 24, 2023]. Retrieved from the Internet <https://dl.acm.org/doi/pdf/10.1145/357290.357293>., Jan. 1982, 18… [cited by applicant]
Demir, Ilke et al., “Proceduralization for Editing 3D Architectural Models”, Fourth International Conference on 3D Vision (3DV) [retrieved Mar. 24, 2023]. Retrieved from the Internet <https://www.cs.purdue.edu/homes/bbe… [cited by applicant]
Deschaintre, Valentin et al., “Flexible SVBRDF Capture with a Multi-Image Deep Network”, Cornell University arXiv, arXiv.org [retrieved Mar. 24, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/1906.11557.pdf>.… [cited by applicant]
Deschaintre, Valentin et al., “Guided Fine-Tuning for Large-Scale Material Transfer”, Cornell University arXiv, arXiv.org [retrieved Mar. 24, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2007.03059.pdf>., J… [cited by applicant]
Deschaintre, Valentin et al., “Single-Image SVBRDF Capture with a Rendering-Aware Deep Network”, Cornell University arXiv, arXiv.org [retrieved Mar. 24, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/1810.097… [cited by applicant]
Deussen, Oliver et al., “Realistic modeling and rendering of plant ecosystems”, SIGGRAPH '98: Proceedings of the 25th annual conference on Computer graphics and interactive techniques [retrieved May 11, 2023]. Retrieved… [cited by applicant]
Du, Tao et al., “InverseCSG: automatic conversion of 3D models to CSG trees”, ACM Transactions on Graphics, vol. 37, No. 6 [retrieved from the Internet <https://doi.org/10.1145/3272127.3275006>, Dec. 2018, 16 pages. [cited by applicant]
Ellis, Kevin et al., “Learning to Infer Graphics Programs from Hand-Drawn Images”, Advances in neural information processing systems 31 [retrieved Mar. 24, 2023]. Retrieved from the Internet <https://par.nsf.gov/servlet… [cited by applicant]
Ellis, Kevin et al., “Write, Execute, Assess: Program Synthesis with a REPL”, Advances in Neural Information Processing Systems 32 [retrieved Mar. 24, 2023]. Retrieved from the Internet <https://proceedings.neurips.cc/p… [cited by applicant]
Fish, Noa et al., “Meta-representation of Shape Families”, ACM Transactions on Graphics, vol. 33, No. 4 [retrieved Dec. 16, 2022]. Retrieved from the Internet <https://doi.org/10.1145/2601097.2601185>, Jul. 2014, 11 pag… [cited by applicant]
Ganin, Yaroslav et al., “Synthesizing Programs for Images using Reinforced Adversarial Learning”, arXiv Preprint, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/1804.01118.pdf>.,… [cited by applicant]
Gao, Duan et al., “Deep inverse rendering for high-resolution SVBRDF estimation from an arbitrary number of images”, ACM Transactions on Graphics, vol. 38, No. 4 [retrieved Mar. 25, 2023]. Retrieved from the Internet <h… [cited by applicant]
Guarnera, Dar'ya et al., “BRDF Representation and Acquisition”, 37th Annual Conference of the European Association for Computer Graphics: State of the Art Reports [retrieved Mar. 25, 2023]. Retrieved from the Internet <… [cited by applicant]
Guehl, P , “Semi-Procedural Textures Using Point Process Texture Basis Functions”, Computer Graphics Forum, vol. 39, No. 4 [retrieved Mar. 23, 2023]. Retrieved from the Internet <https://publis.icube.unistra.fr/docs/145… [cited by applicant]
Guerrero, Paul et al., “MatFormer: A Generative Model for Procedural Materials”, Cornell University arXiv, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2207.01044.pdf>., Aug. 1… [cited by applicant]
Guo, Jie et al., “Highlight-Aware Two-Stream Network for Single-Image SVBRDF Acquisition”, ACM Transactions on Graphics, vol. 40, No. 4 [retrieved Apr. 10, 2023]. Retrieved from the Internet <https://sites.cs.ucsb.edu/˜… [cited by applicant]
Guo, Y. et al., “A Bayesian Inference Framework for Procedural Material Parameter Estimation”, Cornell University arXiv, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/1912.01067… [cited by applicant]
Guo, Yu et al., “MaterialGAN: Reflectance Capture using a Generative SVBRDF Model”, Cornell University arXiv, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2010.00114.pdf>., Sep… [cited by applicant]
Heitz, Eric et al., “A Sliced Wasserstein Loss for Neural Texture Synthesis”, Cornell University arXiv, arXiv.org [retrieved Mar. 27, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2006.07229.pdf>., Mar. 11, … [cited by applicant]
Henzler, Philipp et al., “Generative Modelling of BRDF Textures from Flash Images”, Cornell University arXiv, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2102.11861.pdf>., Sep… [cited by applicant]
Hu, Yiwei et al., “A novel framework for inverse procedural texture modeling”, ACM Transactions on Graphics, vol. 38, No. 6 [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://graphics.cs.yale.edu/sites/defa… [cited by applicant]
Hu, Yiwei et al., “An Inverse Procedural Modeling Pipeline for SVBRDF Maps”, Cornell University arXiv, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2109.06395.pdf>., Sep. 27, 2… [cited by applicant]
Hu, Yiwei et al., “Controlling Material Appearance by Examples”, Cornell University arXiv, arXiv.org [retrieved Mar. 28, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2206.14970.pdf>., Jun. 30, 2022, 12 Page… [cited by applicant]
Hu, Yiwei et al., “Node Graph Optimization Using Differentiable Proxies”, SIGGRAPH '22: ACM SIGGRAPH 2022 Conference Proceedings [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2207.07684.p… [cited by applicant]
Hu, Yuanming et al., “Exposure: A White-Box Photo Post-Processing Framework”, ACM Transactions on Graphics, vol. 37, No. 2 [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://web.archive.org/web/202003221604… [cited by applicant]
Huang, Haibin , “Deep-Learned Generative Representations Of 3D Shape Families”, University of Massachusetts Amherst, College of Information and Computer Sciences [retrieved May 12, 2023]. Retrieved from the Internet <ht… [cited by applicant]
Huang, Haibin et al., “Shape Synthesis from Sketches via Procedural Models and Convolutional Networks”, IEEE Transactions On Visualization and Computer Graphics. vol. 23, No. 8,, 2017, 11 pages. [cited by applicant]
Johnson, Justin et al., “Inferring and Executing Programs for Visual Reasoning”, Cornell University arXiv, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/1705.03633.pdf>., May 10… [cited by applicant]
Jones, R. Kenny et al., “ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis”, Cornell University arXiv, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/… [cited by applicant]
Kania, Kacper et al., “UCSG-Net—Unsupervised Discovering of Constructive Solid Geometry Tree”, Advances in Neural Information Processing Systems 33 [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://proceed… [cited by applicant]
Kingma, Diederik P. et al., “Adam: A Method for Stochastic Optimization”, Cornell University, arXiv Preprint, arXiv.org [retrieved Oct. 9, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/1412.6980.pdf>., Jan. … [cited by applicant]
Krs, Vojtech et al., “PICO: Procedural Iterative Constrained Optimizer for Geometric Modeling”, IEEE Transactions on Visualization and Computer Graphics [retrieved on Oct. 2, 2020]. Retrieved from the Internet <https://… [cited by applicant]
Leyk, Stefan et al., “A Conceptual Framework for Uncertainty Investigation in Map-based Land Cover Change Modelling”, Transactions in GIS, vol. 9, No. 3 [retrieved May 12, 2021]. Retrieved from the Internet <https://doi… [cited by applicant]
Li, Xiao et al., “Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networks”, Cornell University arXiv, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <htt… [cited by applicant]
Lipp, Markus et al., “Local Editing of Procedural Models”, Wiley Online Library, Computer Graphics Forum vol. 38, Issue 2, [retrieved on Oct. 2, 2020]. Retrieved from the Internet <https://doi.org/10.1111/cgf.13615>., J… [cited by applicant]
Liu, Albert Julius et al., “Simulating the Structure and Texture of Solid Wood”, ACM Transactions on Graphics, vol. 35, No. 6 [retrieved Mar. 25, 2023]. Retrieved from the Internet <http://www.cs.cornell.edu/projects/wo… [cited by applicant]
Lu, Sidi et al., “Neurally-Guided Structure Inference”, Cornell University arXiv, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <http://128.84.21.203/pdf/1906.07304>., Aug. 15, 2019, 11 Pages. [cited by applicant]
Nishida, Gen et al., “Interactive Sketching of Urban Procedural Models”, ACM Trans. Graph., vol. 35, No. 4, Article 130, 2016, 11 pages. [cited by applicant]
Radford, Alec et al., “Learning Transferable Visual Models From Natural Language Supervision”, Cornell University arXiv, arXiv.org [retrieved Jun. 29, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2103.00020… [cited by applicant]
Ramesh, Aditya et al., “Hierarchical Text-Conditional Image Generation with CLIP Latents”, Cornell University arXiv, arXiv.org [retrieved Aug. 11, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2204.06125.pdf… [cited by applicant]
Rombach, Robin et al., “High-Resolution Image Synthesis with Latent Diffusion Models”, Cornell University arXiv, arXiv.org [retrieved Aug. 11, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2112.10752.pdf>., … [cited by applicant]
Sharma, Gopal et al., “CSGNet: Neural Shape Parser for Constructive Solid Geometry”, arXiv Preprint, Cornell University, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/1712.08290… [cited by applicant]
Shi, Liang et al., “Match: differentiable material graphs for procedural material capture”, Association for Computing Machinery [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://dspace.mit.edu/handle/1721.… [cited by applicant]
Št'ava, O. et al., “Inverse Procedural Modeling by Automatic Generation of L-systems”, Computer Graphics Forum, vol. 29, No. 2 [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://citeseerx.ist.psu.edu/docume… [cited by applicant]
Tian, Yonglong et al., “Learning to Infer and Execute 3D Shape Programs”, Cornell University arXiv, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/1901.02875.pdf>., Aug. 9, 2019,… [cited by applicant]
Vaswani, Ashish et al., “Attention Is All You Need”, Cornell University arXiv Preprint, arXiv.org [retrieved Aug. 9, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/1706.03762.pdf>., Dec. 6, 2017, 15 pages. [cited by applicant]
Vinyals, Oriol et al., “Pointer Networks”, Advances in Neural Information Processing Systems 28 [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://proceedings.neurips.cc/paper_files/paper/2015/file/29921001… [cited by applicant]
Walke, Homer et al., “Learning to Infer Shape Programs Using Latent Execution Self Training”, Cornell University arXiv, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2011.13045v… [cited by applicant]
Walter, Bruce et al., “Microfacet Models for Refraction through Rough Surfaces”, Proceedings of the 18th Eurographics Conference on Rendering Techniques, EGSR'07, Goslar, DEU, Eurographics Association [retrieved on Mar.… [cited by applicant]
Wu, Chenming et al., “Carpentry compiler”, ACM Transactions on Graphics, vol. 38, No. 6 [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://grail.cs.washington.edu/wp-content/uploads/2019/11/wu2019cc.pdf>., … [cited by applicant]
Xu, Xianghao et al., “Inferring CAD Modeling Sequences Using Zone Graphs”, Cornell University arXiv, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <http://128.84.21.203/pdf/2104.03900>., Apr. 20, 2021… [cited by applicant]
Ye, Wenjie et al., “Deep Reflectance Scanning: Recovering Spatially-varying Material Appearance from a Flash-lit Video Sequence”, Computer Graphics Forum, vol. 40, No. 6 [retrieved Mar. 25, 2023]. Retrieved from the Int… [cited by applicant]
Yumer, Mehmet E. et al., “Procedural Modeling Using Autoencoder Networks”, UIST '15: Proceedings of the 28th Annual ACM Symposium on User Interface Software & Technology [retrieved Dec. 16, 2022]. Retrieved from the Int… [cited by applicant]
Zhou, Xilong et al., “Adversarial Single-Image SVBRDF Estimation with Hybrid Training”, Computer Graphics Forum, vol. 40, No. 2 [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://people.engr.tamu.edu/nimak/… [cited by applicant]
Zhou, Xilong et al., “TileGen: Tileable, Controllable Material Generation and Capture”, Cornell University arXiv, arXiv.org [retrieved Mar. 25, 2023]. Retrieved from the Internet <https://arxiv.org/pdf/2206.05649.pdf>.,… [cited by applicant]