IP Library › Granted Patent US 12,374,034
Granted Patent B2
US 12,374,034 · App. 18/168,995 · Granted Jul 29, 2025

Generating soft object shadows for general shadow receivers within digital images using geometry-aware buffer channels

Inventors: Jianming Zhang (Campbell, CA); Yichen Sheng (West Lafayette, IN); Julien Philip (London, GB); Yannick Hold-Geoffroy (Quebec City, CA); Xin Sun (Sunnyvale, CA); He Zhang (San Jose, CA)
Assignee: Adobe Inc.
G06T15/60G06T7/60G06V10/60G06V10/761G06V10/82
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 12,374,034
App. No.
18/168,995
Granted
Jul 29, 2025
Kind
B2
Abstract

The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates object shadows for digital images utilizing corresponding geometry-aware buffer channels. For instance, in one or more embodiments, the disclosed systems generate, utilizing a height prediction neural network, an object height map for a digital object portrayed in a digital image and a background height map for a background portrayed in the digital image. The disclosed systems also generate, from the digital image, a plurality of geometry-aware buffer channels using the object height map and the background height map. Further, the disclosed systems modify the digital image to include a soft object shadow for the digital object using the plurality of geometry-aware buffer channels.

Claims (52)

1. A method comprising:

generating, utilizing a height prediction neural network, an object height map for a digital object portrayed in a digital image and a background height map for a background portrayed in the digital image,

wherein the object height map includes pixel heights that indicate vertical distances of pixels associated with the digital object from a ground surface of the digital image within a two-dimensional coordinate scheme of the digital image; and

wherein the background height map includes additional pixel heights that indicate additional vertical distances of pixels associated with the background from the ground surface within the two-dimensional coordinate scheme;

generating, from the digital image, a plurality of geometry-aware buffer channels using the pixel heights included in the object height map and the additional pixel heights included in the background height map; and

modifying the digital image to include a soft object shadow for the digital object using the plurality of geometry-aware buffer channels.

2. The method of claim 1 , wherein generating, from the digital image, the plurality of geometry-aware buffer channels using the pixel heights included in the object height map and the additional pixel heights included in the background height map comprises generating a first geometry-aware buffer channel that includes a first gradient of the additional pixel heights included in the background height map in a first direction.

3. The method of claim 2 , wherein generating, from the digital image, the plurality of geometry-aware buffer channels using the pixel heights included in the object height map and the additional pixel heights included in the background height map comprises generating a second geometry-aware buffer channel that includes a second gradient of the additional pixel heights included in the background height map in a second direction.

4. The method of claim 1 , wherein generating, from the digital image, the plurality of geometry-aware buffer channels using the pixel heights included in the object height map and the additional pixel heights included in the background height map comprises generating a geometry-aware buffer channel that includes relative distances for pixels of the background and corresponding pixels of the digital object utilizing the additional pixel heights included in the object height map.

5. The method of claim 1 , wherein modifying the digital image to include the soft object shadow for the digital object using the plurality of geometry-aware buffer channels comprises modifying the digital image utilizing a shadow stylization neural network to include the soft object shadow for the digital object based on the plurality of geometry-aware buffer channels.

6. The method of claim 1 ,

further comprising determining a softness value for the soft object shadow,

wherein modifying the digital image to include the soft object shadow for the digital object using the plurality of geometry-aware buffer channels comprises modifying the digital image to include the soft object shadow for the digital object using the plurality of geometry-aware buffer channels and the softness value.

7. The method of claim 1 , wherein generating, from the digital image, the plurality of geometry-aware buffer channels comprises generating, from the digital image, one or more geometry-aware buffer channels using at least one of a position of a light source associated with the digital image or a horizon associated with the digital image.

8. The method of claim 1 , wherein generating, from the digital image, the plurality of geometry-aware buffer channels using the pixel heights included in the object height map and the additional pixel heights included in the background height map comprises generating, from the digital image, a geometry-aware buffer channel that includes sparse hard object shadows cast by the digital object in accordance with an area light source associated with digital image.

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

determining, utilizing a height prediction neural network, an object height map for a digital object portrayed in a digital image and a background height map for a background portrayed in the digital image,

wherein the object height map includes pixel heights that indicate vertical distances of pixels associated with the digital object from a ground surface of the digital image within a two-dimensional coordinate scheme of the digital image; and

wherein the background height map includes additional pixel heights that indicate additional vertical distances of pixels associated with the background from the ground surface within the two-dimensional coordinate scheme;

determining, from the digital image, a plurality of geometry-aware buffer channels using pixel heights included in the object height map and the additional pixel heights included in the background height map; and

modifying the digital image to include a soft object shadow for the digital object using the plurality of geometry-aware buffer channels.

10. The non-transitory computer-readable medium of claim 9 , wherein determining, from the digital image, the plurality of geometry-aware buffer channels using the pixel heights included in the object height map and the additional pixel heights included in the background height map comprises generating a geometry-aware buffer channel that includes relative pixel height differences for pixels of the background and corresponding pixels of the digital object utilizing the pixel heights included in the object height map and the additional pixel heights included in the background height map.

11. The non-transitory computer-readable medium of claim 10 , wherein determining the geometry-aware buffer channel that includes the relative pixel height differences for the pixels of the background and the corresponding pixels of the digital object utilizing the pixel heights included in the object height map and the additional pixel heights included in the background height map comprises:

determining a first pixel height for a pixel of the background using the additional pixel heights included in the background height map;

determining a second pixel height for a pixel of the digital object that corresponds to the pixel of the background using the pixel heights included in the object height map; and

determining a height difference between the first pixel height and the second pixel height.

12. The non-transitory computer-readable medium of claim 11 , wherein the operations further comprise determining the pixel of the digital object that corresponds to the pixel of the background by determining that the pixel of the digital object is blocking light from reaching the pixel of the background.

13. The non-transitory computer-readable medium of claim 9 , wherein:

determining, from the digital image, a plurality of geometry-aware buffer channels using the pixel heights included in the object height map and the additional pixel heights included in the background height map comprises generating a geometry-aware buffer channel that includes a hard object shadow for the digital object using the pixel heights included in the object height map and the additional pixel heights included in the background height map; and

modifying the digital image to include the soft object shadow for the digital object using the plurality of geometry-aware buffer channels comprises modifying the hard object shadow of the geometry-aware buffer channel to generate the soft object shadow within the digital image.

14. The non-transitory computer-readable medium of claim 9 , wherein determining, from the digital image, the plurality of geometry-aware buffer channels using the pixel heights included in the object height map and the additional pixel heights included in the background height map comprises generating geometry-aware buffer channels that are translation invariant by generating one or more geometry-aware buffer channels that include a gradient of the additional pixel heights included in the background height map.

15. The non-transitory computer-readable medium of claim 9 , wherein determining, from the digital image, the plurality of geometry-aware buffer channels using the pixel heights included in the object height map and the additional pixel heights included in the background height map comprises generating a geometry-aware buffer channel that includes relative distances for pixels of the background and corresponding pixels of the digital object utilizing the pixel heights included in the object height map, a relative distance for a pixel of the background and a corresponding pixel of the digital object comprising a distance between the pixel of the background and a ground point corresponding to the pixel of the digital object.

16. A system comprising:

one or more memory components; and

one or more processing devices coupled to the one or more memory components, the one or more processing devices to perform operations comprising:

receiving a digital image portraying a digital object against a non-planar background;

generating, utilizing a height prediction neural network, an object height map for the digital object and a background height map for the non-planar background of the digital image,

wherein the object height map includes pixel heights that indicate vertical distances of pixels associated with the digital object from a ground surface of the digital image; and

wherein the background height map includes additional pixel heights that indicate additional vertical distances of pixels associated with the non-planar background from the ground surface;

generating a first geometry-aware buffer channel that includes a hard object shadow for the digital object using the pixel heights included in the object height map;

generating a second geometry-aware buffer channel that includes a gradient of the additional pixel heights included in the background height map; and

modifying the digital image to include a soft object shadow for the digital object across the non-planar background using the first geometry-aware buffer channel and the second geometry-aware buffer channel.

17. The system of claim 16 , wherein:

generating the second geometry-aware buffer channel that includes the gradient of the additional pixel heights included in the background height map comprises generating the second geometry-aware buffer channel that includes a first gradient of the additional pixel heights included in the background height map in an x-direction; and

the one or more processing devices further perform operations comprising generating a third geometry-aware buffer channel that includes a second gradient of the additional pixel heights included in the background height map in a y-direction.

18. The system of claim 17 , wherein:

the one or more processing devices further perform operations comprising generating a fourth geometry-aware buffer channel that includes an object cutout corresponding to the digital object; and

modifying the digital image to include the soft object shadow for the digital object across the non-planar background using the first geometry-aware buffer channel and the second geometry-aware buffer channel comprises modifying the digital image to include the soft object shadow using the first geometry-aware buffer channel, the second geometry-aware buffer channel, the third geometry-aware buffer channel, and the fourth geometry-aware buffer channel.

19. The system of claim 16 , wherein modifying the digital image to include the soft object shadow for the digital object across the non-planar background comprises modifying the digital image to include the soft object shadow across a first surface and a second surface of the non-planar background, wherein the first surface is associated with a first plane portrayed within the digital image and the second surface is associated with a second plane portrayed within the digital image.

20. The system of claim 16 , wherein:

the one or more processing devices further perform operations comprising receiving a softness value for the soft object shadow from a client device; and

modifying the digital image to include the soft object shadow for the digital object across the non-planar background using the first geometry-aware buffer channel and the second geometry-aware buffer channel comprises modifying, using a shadow stylization neural network, the digital image to include the soft object shadow using first geometry-aware buffer channel, the second geometry-aware buffer channel, and the softness value.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 14, 2023
From: ZHANG, JIANMING; SHENG, YICHEN; PHILIP, JULIEN; HOLD-GEOFFROY, YANNICK; SUN, XIN; ZHANG, HE
To: ADOBE INC.
Reel/Frame 062696/0086 →
Continuity (1)
Related Publication 20240273813A1 · Aug 15, 2024
References Cited (70)
US 8379021B1 · Miller · 2013 [cited by examiner]
US 11335004B2 · Liu et al. · 2022 [cited by applicant]
US 20150348315A1 · Wang · 2015 [cited by examiner]
US 20220092812A1 · Boudreaux · 2022 [cited by examiner]
US 20220292684A1 · Wang et al. · 2022 [cited by applicant]
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, 970 James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. Pytorch: An imperative style, high-performance deep learning l… [cited by applicant]
Angel X Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, et al. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv… [cited by applicant]
Angjoo Kanazawa, Michael J Black, David W Jacobs, and Jitendra Malik. End-to-end recovery of human shape and pose. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7122-7131, 2018. [cited by applicant]
Ayan Sinha, Asim Unmesh, Qixing Huang, and Karthik Ramani. Surfnet: Generating 3d shape surfaces using deep residual networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6040-6… [cited by applicant]
Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, Jonathan T. Barron, Ravi Ramamoorthi, and Ren Ng. NeRF: representing scenes as neural radiance fields for view synthesis. Communications of the ACM, 65(1):99-106, Ja… [cited by applicant]
Chen Kong, Chen-Hsuan Lin, and Simon Lucey. Using locally corresponding cad models for dense 3d reconstructions from a single image. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. … [cited by applicant]
Christoph Lassner, Javier Romero, Martin Kiefel, Federica Bogo, Michael J Black, and Peter V Gehler. Unite the people: Closing the loop between 3d and 2d human representations. In Proceedings of the IEEE conference on c… [cited by applicant]
Cyril Soler and Francois X. Sillion. Fast calculation of soft shadow textures using convolution. In Proceedings of the 25th annual conference on Computer graphics and interactive techniques—SIGGRAPH '98, pp. 321-332, No… [cited by applicant]
Daquan Liu, Chengjiang Long, Hongpan Zhang, Hanning Yu, Xinzhi Dong, and Chunxia Xiao. Arshadowgan: Shadow generative adversarial network for augmented reality in single light scenes. In Proceedings of the IEEE/CVF Conf… [cited by applicant]
David Griffiths, Tobias Ritschel, and Julien Philip. Out-cast: Single image relighting with cast shadows. Computer Graphics Forum, 43, 2022. [cited by applicant]
Donglai Xiang, Hanbyul Joo, and Yaser Sheikh. Monocular Total Capture: Posing Face, Body, and Hands in the Wild. In 2019 IEEE/CVF Conference on Computer Vision and Pat-tern Recognition (CVPR), pp. 10957-10966, Long Beac… [cited by applicant]
E. Reinhard, M. Adhikhmin, B. Gooch, and P. Shirley. Color transfer between images. IEEE Computer Graphics and Ap-plications, 21(5):34-41, Jul. 2001. Conference Name: IEEE Computer Graphics and Applications. [cited by applicant]
Eric Chan and Fredo Durand. Rendering Fake Soft Shadows with Smoothies. p. 12. [cited by applicant]
F. Pitie, A.C. Kokaram, and R. Dahyot. N-dimensional prob- bility density function transfer and its application to color transfer. In Tenth IEEE International Conference on Computer Vision (ICCV'05) vol. 1, vol. 2, pp. … [cited by applicant]
Federica Bogo, Angjoo Kanazawa, Christoph Lassner, Peter Gehler, Javier Romero, and Michael J Black. Keep it smpl: Automatic estimation of 3d human pose and shape from a single image. In European conference on computer … [cited by applicant]
Francois X Sillion, James Arvo, Stephen Westin, and Donald P Greenberg. A Global Illumination Solution for General Reflectance Distributions. Computer Graphics, 25(4):11, 1991. [cited by applicant]
Gael Guennebaud, Loic Barthe, and Mathias Paulin. High-Quality Adaptive Soft Shadow Mapping. Computer Graph-ics Forum, 26(3):525-533, Sep. 2007. [cited by applicant]
Gael Guennebaud, Loic Barthe, and Mathias Paulin. Real-time soft shadow mapping by backprojection. p. 8. [cited by applicant]
Georgios Pavlakos, Vasileios Choutas, Nima Ghorbani, Timo Bolkart, Ahmed A. Osman, Dimitrios Tzionas, and Michael J. Black. Expressive Body Capture: 3D Hands, Face, and Body From a Single Image. In 2019 IEEE/CVF Confere… [cited by applicant]
Hao Zhou, Sunil Hadap, Kalyan Sunkavalli, and David Ja-cobs. Deep Single-Image Portrait Relighting. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 7193-7201, Seoul, Korea (South), Oct. 2019. IE… [cited by applicant]
James T Kajiya. The rendering equation. In Proceedings of the 13th annual conference on Computer graphics and interactive techniques, pp. 143-150, 1986. [cited by applicant]
Jeya Maria Jose Valanarasu, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Jose Echevarria, Yinglan Ma, Zijun Wei, Kalyan Sunkavalli, and Vishal M Patel. Interactive portrait harmonization. arXiv preprint arXiv:2203.082… [cited by applicant]
Jhony K Pontes, Chen Kong, Anders Eriksson, Clinton Fookes, Sridha Sridharan, and Simon Lucey. Compact model representation for 3d reconstruction. arXiv preprint arXiv:1707.07360, 2017. [cited by applicant]
Jhony K Pontes, Chen Kong, Sridha Sridharan, Simon Lucey, Anders Eriksson, and Clinton Fookes. Image2mesh: A learning framework for single image 3d reconstruction. In Asian Conference on Computer Vision, pp. 365-381. Sp… [cited by applicant]
Jiaya Jia, Jian Sun, Chi-Keung Tang, and Heung-Yeung Shum. Drag-and-drop pasting. ACM Transactions on Graphics, 25(3):631-637, Jul. 2006. [cited by applicant]
Julien Philip, Michael Gharbi, Tinghui Zhou, Alexei A Efros, and George Drettakis. Multi-view relighting using a geometry-aware network. ACM Trans. Graph., 38(4):78-1, 2019. [cited by applicant]
Julien Philip, Sebastien Morgenthaler, Michael Gharbi, and George Drettakis. Free-viewpoint indoor neural relighting from multi-view stereo. ACM Transactions on Graphics (TOG), 40(5):1-18, 2021. [cited by applicant]
Jun Ling, Han Xue, Li Song, Rong Xie, and Xiao Gu. Region-aware adaptive instance normalization for image harmonization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9361-994… [cited by applicant]
Konstantin Sofiiuk, Polina Popenova, and Anton Konushin. Foreground-aware semantic representations for image harmonization. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1620-1… [cited by applicant]
Lance Williams. Casting Curved Shadows on Curved Surfaces. p. 5. [cited by applicant]
Marc Stamminger and George Drettakis. Perspective shadow maps. In John Hughes, editor, Proceedings of ACM SIGGRAPH, Annual Conference Series, pp. 557-562. ACM Press/ ACM SIGGRAPH, Jul. 2002. [cited by applicant]
Michael Schwarz and Marc Stamminger. Bitmask Soft Shadows. Computer Graphics Forum, 26(3):515-524, Sep. 2007. [cited by applicant]
Michael W. Tao, Micah K. Johnson, and Sylvain Paris. Error Tolerant Image Compositing. In Kostas Daniilidis, Petros Maragos, and Nikos Paragios, editors, Computer Vision—ECCV 2010, Lecture Notes in Computer Science, pp.… [cited by applicant]
Patrick Perez, Michel Gangnet, and Andrew Blake. Poisson image editing. In ACM SIGGRAPH 2003 Papers, pp. 313-318. 2003. [cited by applicant]
Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A Efros. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1125-… [cited by applicant]
Pradeep Sen, Mike Cammarano, and Pat Hanrahan. Shadow silhouette maps. ACM Transactions on Graphics (TOG), 22(3):521-526, 2003. [cited by applicant]
Pratul P. Srinivasan, Boyang Deng, Xiuming Zhang, Matthew Tancik, Ben Mildenhall, and Jonathan T. Barron. NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis. In 2021 IEEE/CVF Conference on … [cited by applicant]
Randima Fernando. Percentage-closer soft shadows. In ACM SIGGRAPH 2005 Sketches on—SIGGRAPH '05, p. 35, Los Angeles, California, 2005. ACM Press. [cited by applicant]
Ren Ng, Ravi Ramamoorthi, and Pat Hanrahan. All Frequency Shadows Using Non-linear Wavelet Lighting Approximation. p. 6. [cited by applicant]
Ricardo Martin-Brualla, Noha Radwan, Mehdi S. M. Sajjadi, Jonathan T. Barron, Alexey Dosovitskiy, and Daniel Duckworth. NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections. In 2021 IEEE/CVF Conf… [cited by applicant]
Richard Zhang, Jun-Yan Zhu, Phillip Isola, Xinyang Geng, Angela S. Lin, Tianhe Yu, and Alexei A. Efros. Real-Time User-Guided Image Colorization with Learned Deep Priors. Technical Report arXiv:1705.02999, arXiv, May 20… [cited by applicant]
Robert L Cook, Thomas Porter, and Loren Carpenter. Computer Graphics vol. 18, No. 3 Jul. 1984. p. 9, 1984. [cited by applicant]
Shunsuke Saito, Tomas Simon, Jason Saragih, and Hanbyul Joo. Pifuhd: Multi-level pixel-aligned implicit function for high-resolution 3d human digitization. In Proceedings of 1026 the IEEE/CVF Conference on Computer Visi… [cited by applicant]
Shunsuke Saito, Zeng Huang, Ryota Natsume, Shigeo Morishima, Angjoo Kanazawa, and Hao Li. Pifu: Pixel-aligned implicit function for high-resolution clothed human digitization. In Proceedings of the IEEE/CVF Internationa… [cited by applicant]
Shuyang Zhang, Runze Liang, and Miao Wang. Shadowgan: Shadow synthesis for virtual objects with conditional adversarial networks. Computational Visual Media, 5(1):105-115, 2019. [cited by applicant]
Stephen H Westin, James R Arvo, and Kenneth E Torrance. Predicting Reflectance Functions from Complex Surfaces. p. 10. [cited by applicant]
Thomas Annen, Zhao Dong, Tom Mertens, Philippe Bekaert, Hans-Peter Seidel, and Jan Kautz. Real-time, all-frequency shadows in dynamic scenes. ACM Transactions on Graphics, 27(3):1-8, Aug. 2008. [cited by applicant]
Tiancheng Sun, Jonathan T. Barron, Yun-Ta Tsai, Zexiang Xu, Xueming Yu, Graham Fyffe, Christoph Rhemann, Jay Busch, Paul Debevec, and Ravi Ramamoorthi. Single image portrait relighting. ACM Transactions on Graphics, 38(… [cited by applicant]
Ulf Assarsson and Tomas Akenine-Moller. A Geometry-based Soft Shadow vol. Algorithm using Graphics Hard-ware. p. 10. [cited by applicant]
Viktor Rudnev, Mohamed Elgharib, William Smith, Lingjie Liu, Vladislav Golyanik, and Christian Theobalt. NeRF for Outdoor Scene Relighting. In Shai Avidan, Gabriel Brostow, Moustapha Cissé, Giovanni Maria Farinella, and… [cited by applicant]
Wenyan Cong, Jianfu Zhang, Li Niu, Liu Liu, Zhixin Ling, Weiyuan Li, and Liqing Zhang. Dovenet: Deep image harmonization via domain verification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern … [cited by applicant]
Wikipedia. Fresnel equations. https://en.wikipedia.org/wiki/Fresnel_equations. [cited by applicant]
William Donnelly and Andrew Lauritzen. Variance shadow maps. In Proceedings of the 2006 symposium on Interactive 3D graphics and games—SI3D '06, p. 161, Redwood City, California, 2006. ACM Press. [cited by applicant]
William T Reeves, David H Salesin, and Robert L Cook. Rendering antialiased shadows with depth maps. In Proceedings of the 14th annual conference on Computer graphics and interactive techniques, pp. 283-291, 1987. [cited by applicant]
Xiaowei Hu, Yitong Jiang, Chi-Wing Fu, and Pheng-Ann Heng. Mask-shadowgan: Learning to remove shadows from unpaired data. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2472-2481, 2019. [cited by applicant]
Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Xin Lu, and Ming-Hsuan Yang. Deep Image Harmonization. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2799-2807, Honolulu, HI, Jul… [cited by applicant]
Yichen Sheng, Jianming Zhang, and Bedrich Benes. Ssn: Soft shadow network for image compositing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4380-4390, 2021. [cited by applicant]
Yichen Sheng, Yifan Liu, Jianming Zhang, Wei Yin, A Cengiz Oztireli, He Zhang, Zhe Lin, Eli Shechtman, and Bedrich Benes. Controllable shadow generation using pixel height maps. In European Conference on Computer Vision… [cited by applicant]
Yifan Jiang, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Kalyan Sunkavalli, Simon Chen, Sohrab Amirghodsi, Sarah Kong, and Zhangyang Wang. SSH: A Self-Supervised Framework for Image Harmonization. In 2021 IEEE/CVF. p… [cited by applicant]
Yifan Liu, Zengchang Qin, Tao Wan, and Zhenbo Luo. Auto-painter: Cartoon image generation from sketch by using conditional wasserstein generative adversarial networks. Neuro-computing, 311:78-87, 2018. [cited by applicant]
Yifan Wang, Brian L Curless, and Steven M Seitz. People as scene probes. In European Conference on Computer Vision, pp. 438-454. Springer, 2020. [cited by applicant]
Yuanlu Xu, Song-Chun Zhu, and Tony Tung. DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 7759-7769, Seoul, Korea (South)… [cited by applicant]
Zerong Zheng, Tao Yu, Yixuan Wei, Qionghai Dai, and Yebin Liu. Deephuman: 3d human reconstruction from a single image. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7739-7749, 2019. [cited by applicant]
Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Lin- guang Zhang, Xiaoou Tang, and Jianxiong Xiao. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision a… [cited by applicant]
Zhixin Shu, Sunil Hadap, Eli Shechtman, Kalyan Sunkavalli, Sylvain Paris, and Dimitris Samaras. Portrait Lighting Transfer Using a Mass Transport Approach. ACM Transactions on Graphics, 37(1):2:1-2:15, Oct. 2017. [cited by applicant]