IP Library › Granted Patent US 12,705,825
Granted Patent B2
US 12,705,825 · App. 18/889,075 · Granted Aug 11, 2026

Volumetric re-lighting of 3D objects

Inventors: He Zhang (Santa Clara, CA); Zhixin Shu (San Jose, CA); Yiqun Mei (Baltimore, MD); Xuaner Zhang (Cupertino, CA); Sai Bi (San Jose, CA); Jianming Zhang (Campbell, CA)
Assignee: Adobe Inc.
G06T15/506G06T7/70G06T15/04G06T2200/04G06T2207/20081G06T2207/20084G06T2207/30201G06T2215/12
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 12,705,825
App. No.
18/889,075
Filed
Sep 18, 2024
Granted
Aug 11, 2026
Kind
B2
Art Unit
2617
USPC
345/426
Abstract

Techniques for volumetric re-lighting of 3D objects are disclosed. In an example method, a computing system receives a first image of a three-dimensional (“3D”) object. The computing system generates a de-lighted image of the 3D object based on the first image. The computing system generates an embedded representation of the 3D object based on the de-lighted image and a first representation of the de-lighted image based on the embedded representation using a first machine learning (“ML”) model. The computing system generates a second representation of the 3D object using a second ML model based on orientation and lighting information and one or more internal states of the first ML model. The computing system generates a third representation of the 3D object by combining the first and second representations. The computing system renders a second image of the 3D object based on the third representation of the 3D object.

Claims (61)

1 . A method performed by one or more processing devices, comprising:

receiving a first image of a three-dimensional (“3D”) object;

generating a de-lighted image of the 3D object based on the first image;

generating an embedded representation of the 3D object based on the de-lighted image using a first machine learning (“ML”) model;

generating a first representation of the de-lighted image based on the embedded representation using the first ML model;

generating a second representation of the 3D object using a second ML model based on orientation information about the 3D object and lighting information, wherein the second ML model is configured using one or more internal states of the first ML model;

generating a third representation of the 3D object by combining the first representation of the de-lighted image and the second representation of the 3D object; and

rendering a second image of the 3D object based on the third representation of the 3D object.

2 . The method of claim 1 , wherein the first image is a photograph, and the 3D object is a portrait.

3 . The method of claim 1 , wherein the de-lighted image is an albedo image.

4 . The method of claim 3 , wherein generating the de-lighted image of the 3D object comprises:

generating a normal image of the 3D object based on the first image using a third ML model; and

generating the de-lighted image of the 3D object based on the first image and the normal image using a fourth ML model.

5 . The method of claim 4 , wherein the third and fourth ML models each comprise a convolutional neural network (“CNN”).

6 . The method of claim 5 , wherein the CNN is based on a U-net architecture.

7 . The method of claim 1 , wherein:

the first ML model is a generative adversarial network (“GAN”); and

generating the embedded representation of the 3D object using the first ML model comprises computing the embedded representation using a GAN inversion operation.

8 . The method of claim 7 , wherein the one or more internal states of the first ML model comprise one or more features of the GAN.

9 . The method of claim 1 , wherein the orientation information about the 3D object comprises a rotation of the 3D object.

10 . The method of claim 9 , wherein the rotation of the 3D object is represented using a rotation matrix.

11 . The method of claim 1 , wherein the lighting information is represented using an environment map.

12 . The method of claim 1 , wherein the second ML model comprises a convolution layer, a residual block, and an upsample block.

13 . The method of claim 1 , wherein the first representation of the de-lighted image, the second representation of the 3D object, and the third representation of the 3D object are tri-planes.

14 . The method of claim 1 , wherein training the second ML model comprises:

generating a set of training data including a plurality of input training images and corresponding output training images;

generating a de-lighted training image for each training input image of the set of training data;

modifying each de-lighted training image based the corresponding input training image;

training the first ML model using each modified de-lighted training image and corresponding output training image; and

training the second ML model using one or more internal states of the trained first ML model.

15 . A system comprising:

one or more processors; and

one or more computer-readable storage media storing instructions which, when executed by the one or more processors, cause the one or more processors to perform operations including:

receiving a first image of a 3D portrait;

generating a de-lighted image of the 3D portrait based on the first image;

generating an embedded representation of the 3D portrait based on the de-lighted image using a first ML model;

generating a first representation representing the de-lighted image based on the embedded representation using the first ML model;

generating a second representation representing the 3D portrait using a second ML model based on orientation information about the 3D portrait and lighting information, wherein the second ML model is configured using one or more internal states of the first ML model;

generating a third representation representing the 3D portrait by combining the first representation representing the de-lighted image and the second representation representing the 3D portrait; and

rendering a second image of the 3D portrait based on the third representation representing the 3D portrait.

16 . The system of claim 15 , wherein:

the de-lighted image is an albedo image; and

generating the de-lighted image of the 3D portrait comprises:

generating a normal image of the 3D portrait based on the first image using a third ML model; and

generating the de-lighted image of the 3D portrait based on the first image and the normal image using a fourth ML model.

17 . The system of claim 15 , wherein:

the first ML model is a generative adversarial network (“GAN”);

generating the embedded representation of the 3D portrait using the first ML model comprises computing the embedded representation using a GAN inversion operation; and

the one or more internal states of the first ML model comprise one or more features of the GAN.

18 . The system of claim 15 , wherein the first representation of the de-lighted image, the second representation of the 3D portrait, and the third representation of the 3D portrait are tri-planes.

19 . A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations including:

a step for generating a de-lighted image based on an image of a 3D object;

a step for generating an embedded representation of the 3D object based on the de-lighted image using a first ML model;

a step for generating a first tri-plane representation of the de-lighted image based on the embedded representation using the first ML model;

a step for generating a second tri-plane representation of the 3D object using a second ML model based on orientation information about the 3D object and lighting information, wherein the second ML model is configured using one or more internal states of the first ML model;

a step for generating a third tri-plane representation of the 3D object by combining the first tri-plane representation of the de-lighted image and the second tri-plane representation of the 3D object; and

a step for rendering a second image of the 3D object based on the third tri-plane representation of the 3D object.

20 . The non-transitory computer-readable medium of claim 19 , wherein:

the first ML model is a generative adversarial network (“GAN”);

generating the embedded representation of the 3D object using the first ML model comprises computing the embedded representation using a GAN inversion operation; and

the one or more internal states of the first ML model comprise one or more features of the GAN.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 18, 2024
From: ZHANG, HE; SHU, ZHIXIN; MEI, YIQUN; ZHANG, XUANER; BI, SAI; ZHANG, JIANMING
To: ADOBE INC.
Reel/Frame 068628/0154 →
Continuity (1)
Related Publication 20260080609A1 · Mar 19, 2026
References Cited (92)
US 11670042B2 · Boubekeur · 2023 [cited by examiner]
US 11704865B2 · Villegas · 2023 [cited by examiner]
US 20210295571A1 · Sun · 2021 [cited by examiner]
US 20220157014A1 · Sevastopolskiy · 2022 [cited by examiner]
US 20250259346A1 · Kim · 2025 [cited by examiner]
Poly Haven, Available online at: https://polyhaven.com/, Accessed from Internet on Aug. 16, 2024, pp. 1-14. [cited by applicant]
Barron et al., Shape, Illumination, and Reflectance from Shading, Institute of Electrical and Electronics Engineers Transactions on Pattern Analysis and Machine Intelligence, vol. 37, No. 8, Dec. 4, 2014, pp. 1-19. [cited by applicant]
Bhattarai et al., TriPlaneNet: An Encoder for EG3D Inversion, Winter Conference on Applications of Computer Vision, 2024, pp. 3055-3065. [cited by applicant]
Bi et al., Deep Relightable Appearance Models for Animatable Faces, Association for Computing Machinery Transactions on Graphics, vol. 40, No. 4, Aug. 2021, pp. 89:1-89:15. [cited by applicant]
Blanz et al., A Morphable Model for the Synthesis of 3D Faces, In Seminal Graphics Papers: Pushing the Boundaries, vol. 2, 2023, 8 pages. [cited by applicant]
Brock et al., Large Scale GAN Training for High Fidelity Natural Image Synthesis, In International Conference on Learning Representations Available Online at: https://arxiv.org/pdf/1809.11096.pdf&org=deepmind, Feb. 25, … [cited by applicant]
Chan et al., Efficient Geometry-aware 3D Generative Adversarial Networks, Computer Vision and Pattern Recognition, Apr. 27, 2022, pp. 1-27. [cited by applicant]
Chan et al., pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis, Computer Vision and Pattern Recognition, Available online at: https://arxiv.org/pdf/2012.00926.pdf, Apr. 5, 2021, 16 p… [cited by applicant]
Chen et al., Learning Implicit Fields for Generative Shape Modeling, In Proceedings of the Institute of Electrical and Electronics Engineers/CVF Conference on Computer Vision and Pattern Recognition, Available online at… [cited by applicant]
Daras et al., Intermediate Layer Optimization for Inverse Problems Using Deep Generative Models, Available online at: https://arxiv.org/pdf/2102.07364, Feb. 15, 2021, 21 pages. [cited by applicant]
Debevec et al., Acquiring the Reflectance Field of a Human Face, In Proceedings of the 27th annual conference on Computer graphics and interactive techniques, 2000, pp. 1-12. [cited by applicant]
Deng et al., Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set, In Proceedings of the Institute of Electrical and Electronics Engineers/CVF conference on computer vision and… [cited by applicant]
Deng et al., GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation, In Proceedings of the Institute of Electrical and Electronics Engineers/CVF conference on computer vision and pattern recognition, 2022, pp… [cited by applicant]
Deng et al., LumiGAN: Unconditional Generation of Relightable 3D Human Faces, In 2024 International Conference on 3D Vision (3DV), Available online at: https://arxiv.org/pdf/2304.13153, Apr. 25, 2023, pp. 302-312. [cited by applicant]
Feng et al., Learning an Animatable Detailed 3D Face Model from in-the-Wild Images, Association for Computing Machinery Transactions on Graphics, vol. 40, No. 4, Aug. 2021, pp. 88:2-88-13. [cited by applicant]
Goodfellow et al., Generative Adversarial Networks, Communications of the Association for Computing Machinery, vol. 63, No. 11, Available online at: https://dl.acm.org/doi/pdf/10.1145/3422622, Nov. 2020, pp. 139-144. [cited by applicant]
Green, Spherical Harmonic Lighting: The Gritty Details, In Archives of the Game Developers Conference, vol. 56, No. 4, Jan. 16, 2003, pp. 1-47. [cited by applicant]
Grey, Master Lighting Guide for Portrait Photographers, Amherst Media, 2014, pp. 1-130. [cited by applicant]
Gu et al., StyleNeRF: A Style-based 3D Aware Generator for High-Resolution Image Synthesis, In International Conference on Learning Representations, Available online at: https://arxiv.org/pdf/2110.08985, Oct. 18, 2021, … [cited by applicant]
Guo et al., The Relightables: Volumetric Performance Capture of Humans with Realistic Relighting, Association for Computing Machinery Transactions on Graphics, vol. 38, No. 6, Nov. 8, 2019, pp. 1-19. [cited by applicant]
Henderson et al., Leveraging 2D Data to Learn Textured 3D Mesh Generation, In Proceedings of the Institute of Electrical and Electronics Engineers/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 749… [cited by applicant]
Henzler, Escaping Plato's Cave: 3D Shape From Adversarial Rendering, International Conference on Computer Vision, Oct. 2019, pp. 9984-9993. [cited by applicant]
Hou et al., Face Relighting with Geometrically Consistent Shadows, In Conference on Computer Vision and Pattern Recognition, 2022, pp. 4217-4226. [cited by applicant]
Hou et al., Towards High Fidelity Face Relighting with Realistic Shadows, Conference on Computer Vision and Pattern Recognition, 2021, pp. 14719-14728. [cited by applicant]
Ji et al., Geometry-Aware Single-Image Full-Body Human Relighting, Available online at: https://arxiv.org/pdf/2207.04750, Jul. 12, 2022, pp. 1-24. [cited by applicant]
Jiang et al., NeRFFacelighting: Implicit and Disentangled Face Lighting Representation Leveraging Generative Prior in Neural Radiance, Association for Computing Machinery Transactions on Graphics, vol. 42, No. 3, Jun. 9… [cited by applicant]
Kanazawa et al., Learning Category-Specific Mesh Reconstruction from Image Collections, Proceedings of the European Conference on Computer Vision (ECCV), Mar. 2018, 16 pages. [cited by applicant]
Karras et al., Analyzing and Improving the Image Quality of StyleGAN, Proceedings of the Institute of Electrical and Electronics Engineers, Conference on Computer Vision and Pattern Recognition, Jun. 14, 2020, pp. 8110-… [cited by applicant]
Ke et al., MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition, In Proceedings of the Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence, vol. 36, No.… [cited by applicant]
Kingma et al., Adam: A Method for Stochastic Optimization, International Conference on Learning Representations, Conference paper at ICLR 2015, Available Online at: https://arxiv.org/pdf/1412.6980.pdf, Jan. 30, 2017, pp… [cited by applicant]
Le et al., Illumination-Invariant Face Recognition with Deep Relit Face Images, Institute of Electrical and Electronics Engineers Winter Conference on Applications of Computer Vision, Jan. 2019, pp. 2146-2155. [cited by applicant]
Li et al., Intrinsic Face Image Decomposition with Human Face Priors, European Conference on Computer Vision, Sep. 2014, pp. 218-233. [cited by applicant]
Ma et al., Rapid Acquisition of Specular and Diffuse Normal Maps From Polarized Spherical Gradient Illumination, Eurographics Symposium on Rendering, Jun. 25, 2007, 12 pages. [cited by applicant]
Mei et al., LightPainter: Interactive Portrait Relighting with Freehand Scribble, Computer Vision and Pattern Recognition, Mar. 2023, pp. 195-205. [cited by applicant]
Meka et al., Deep Relightable Textures: Volumetric Performance Capture with Neural Rendering, Association for Computing Machinery Transactions on Graphics, vol. 39, No. 6, Dec. 2020, pp. 259:1-259:21. [cited by applicant]
Menon et al., PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models, Available online at: https://arxiv.org/abs/2003.03808, Mar. 8, 2020, pp. 2437-2445. [cited by applicant]
Mildenhall et al., NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis, Communications of the Association for Computing Machinery, vol. 65, No. 1, Jan. 2022, pp. 99-106. [cited by applicant]
Nestmeyer et al., Learning Physics-Guided Face Relighting Under Directional Light, Computer Vision and Pattern Recognition, Apr. 19, 2020, pp. 5124-5133. [cited by applicant]
Nguyen-Phuoc et al., HoloGAN: Unsupervised Learning of 3D Representations from Natural Images, Available online at: https://arxiv.org/pdf/1904.01326.pdf, Oct. 1, 2019, 10 pages. [cited by applicant]
Niemeyer et al., GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields, Available online at: https://arxiv.org/pdf/2011.12100.pdf, Apr. 29, 2021, 12 pages. [cited by applicant]
Or-El et al., StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation, Conference on Computer Vision and Pattern Recognition, Mar. 30, 2022, 18 pages. [cited by applicant]
Pan et al., A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis, Available online at: https://arxiv.org/pdf/2110.15678, Dec. 8, 2021, pp. 1-18. [cited by applicant]
Pandey et al., Total Relighting: Learning to Relight Portraits for Background Replacement, Association for Computing Machinery Transactions on Graphics, vol. 40, No. 4, Aug. 2021, pp. 43:1-43:21. [cited by applicant]
Papantoniou et al., Relightify: Relightable 3D Faces from a Single Image via Diffusion Models, Available online at: https://arxiv.org/pdf/2305.06077, Aug. 22, 2023, pp. 1-15. [cited by applicant]
Peers et al., Post-production Facial Performance Relighting Using Reflectance Transfer, Association for Computing Machinery Transactions on Graphics, vol. 26, No. 3, Jul. 2007, pp. 52-1:52-10. [cited by applicant]
Ranjan et al., FaceLit: Neural 3D Relightable Faces, Available online at: https://arxiv.org/pdf/2303.15437, Mar. 27, 2023, 14 pages. [cited by applicant]
Rao et al., VoRF: Volumetric Relightable Faces, Available online at: https://bmvc2022.mpi-inf.mpg.de/0708.pdf, 2022, pp. 1-14. [cited by applicant]
Richardson et al., Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation, Conference on Computer Vision and Pattern Recognition, Apr. 21, 2021, 21 pages. [cited by applicant]
Roich et al., Pivotal Tuning for Latent-based Editing of Real Images, Association for Computing Machinery Transactions on Graphics, vol. 42, No. 1, Aug. 12, 2022, pp. 6:1-6:13. [cited by applicant]
Ronneberger et al., U-Net: Convolutional Networks for Biomedical Image Segmentation, International Conference on Medical Image Computing and Computer-Assisted Intervention, Available Online at URL: https://arxiv.org/pdf… [cited by applicant]
Schriever et al., Complete Self-instructing Library of Practical Photography: Negative Retouching; Etching and Modeling; Encyclopedic Index, American School of Art and Photography, 1909, 504 pages, Chapter XI, “General … [cited by applicant]
Schwarz et al., GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis, Advances in Neural Information Processing Systems, Available online at: https://arxiv.org/abs/2007.02442, Mar. 30, 2021, pp. 1-13. [cited by applicant]
Shahlaei et al., Realistic Inverse Lighting from a Single 2D Image of a Face, Taken Under Unknown and Complex Lighting, 11th Institute of Electrical and Electronics Engineers International Conference and Workshops on Au… [cited by applicant]
Shashua et al., The Quotient Image: Class-Based Re-Rendering and Recognition with Varying Illuminations, Institute of Electrical and Electronics Engineers Transactions on Pattern Analysis and Machine Intelligence, vol. … [cited by applicant]
Shih et al., Style Transfer for Headshot Portraits, Association for Computing Machinery Transactions Graphics vol. 33, No. 4, Jul. 27, 2014, 14 pages. [cited by applicant]
Shu et al., Portrait Lighting Transfer Using a Mass Transport Approach, Association for Computing Machinery Transactions on Graphics. vol. 37, No. 4, Oct. 2017, pp. 2:1-2:15. [cited by applicant]
Simonyan et al., Very Deep Convolutional Networks for Large-Scale Image Recognition, Available online at: https://arxiv.org/abs/1409.1556, Apr. 10, 2015, pp. 1-14. [cited by applicant]
Sun et al., NeLF: Neural Light-transport Field for Portrait View Synthesis and Relighting, Available Online at: https://arxiv.org/pdf/2107.12351, Jul. 26, 2021, 12 pages. [cited by applicant]
Sun et al., Single Image Portrait Relighting, Association for Computing Machinery Transactions on Graphics, vol. 38, No. 4, Jul. 2019, pp. 79:1-79:12. [cited by applicant]
Tan et al., VoLux-GAN: a Generative Model for 3D Face Synthesis with HDRI Relighting, SIGGRAPH '22 Conference Proceedings, Aug. 7-11, 2022, 9 pages. [cited by applicant]
Tewari et al., Monocular Reconstruction of Neural Face Reflectance Fields, In Proceedings of the Institute of Electrical and Electronics Engineers/CVF Conference on Computer Vision and Pattern Recognition 2021, 2021, pp… [cited by applicant]
Wang et al., Free-View Face Relighting Using a Hybrid Parametric Neural Model on a Small-Olat Dataset, International Journal of Computer Vision, vol. 131, No. 3, Jan. 7, 2023, pp. 1002-1021. [cited by applicant]
Wang et al., Image Quality Assessment: from Error Visibility to Structural Similarity, Institute of Electrical and Electronics Engineers Transactions on Image Processing, vol. 13, No. 4, Apr. 13, 2004, pp. 600-612. [cited by applicant]
Wang et al., Single Image Portrait Relighting via Explicit Multiple Reflectance Channel Modeling, Association for Computing Machinery Transactions on Graphics, vol. 39, No. 6, Nov. 27, 2020, pp. 220:1-220:13. [cited by applicant]
Wang et al., Sunstage: Portrait Reconstruction and Relighting Using the Sun as a Light Stage, In Proceedings of the Institute of Electrical and Electronics Engineers/CVF Conference on Computer Vision and Pattern Recogni… [cited by applicant]
Wang et al., Towards Real-world Blind Face Restoration with Generative Facial Prior, In Proceedings of the Institute of Electrical and Electronics Engineers/CVF Conference on Computer Vision and Pattern Recognition 2021… [cited by applicant]
Wenger et al., Performance Relighting and Reflectance Transformation with Time-multiplexed Illumination, Association for Computing Machinery Transactions on Graphics, vol. 24, No. 3, Jul. 1, 2005, pp. 756-764. [cited by applicant]
Wu et al., A Light CNN for Deep Face Representation with Noisy Labels, Institute of Electrical and Electronics Engineers Transactions on Information Forensics and Security, vol. 13, No. 11, Nov. 2018, pp. 2884-2296. [cited by applicant]
Xia et al., GAN Inversion: A Survey, arXiv preprint arXiv:2101.05278, Aug. 13, 2021, 21 pages. [cited by applicant]
Xie et al., High-fidelity 3D Gan Inversion by Pseudo-multi-view Optimization, In proceedings of the Institute of Electrical and Electronics Engineers/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. … [cited by applicant]
Yang et al., 3DHumanGAN: 3D-aware Human Image Generation with 3d Pose Mapping, In proceedings of the Institute of Electrical and Electronics Engineers/CVF International Conference on Computer Vision 2023, 2023, pp. 2300… [cited by applicant]
Yang et al., GAN Prior Embedded Network for Blind Face Restoration in the Wild, In Proceedings of the Institute of Electrical and Electronics Engineers/CVF Conference on Computer Vision and Pattern Recognition 2021, 202… [cited by applicant]
Yang et al., Pastiche Master: Exemplar-based High-resolution Portrait Style Transfer, In Proceedings of the Institute of Electrical and Electronics Engineers/CVF Conference on Computer Vision and Pattern Recognition 202… [cited by applicant]
Yang et al., VToonify: Controllable High-resolution Portrait Video Style Transfer, Association for Computing Machinery Transactions on Graphics, vol. 41, No. 6, Nov. 30, 2022, 15 pages. [cited by applicant]
Yeh et al., Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-real Adaptation, Association for Computing Machinery Transactions on Graphics, vol. 41, No. 6, Nov. 30, 2022, pp. 1-21. [cited by applicant]
Yin et al., 3D Gan Inversion with Facial Symmetry Prior, In proceedings of the Institute of Electrical and Electronics Engineers/CVF Conference on Computer Vision and Pattern Recognition 2023, 2023, pp. 342-351. [cited by applicant]
Yu et al., Free-Form Image Inpainting with Gated Convolution, Available Online at: https://arxiv.org/pdf/1806.03589.pdf, Oct. 22, 2019, 17 pages. [cited by applicant]
Yuan et al., Make Encoder Great Again in 3D Gan Inversion Through Geometry and Occlusion-aware Encoding, In proceedings of the Institute of Electrical and Electronics Engineers/CVF International Conference on Computer V… [cited by applicant]
Zhang et al., 3D-aware Semantic-guided Generative Model for Human Synthesis, In European Conference on Computer Vision, Oct. 23, 2022, pp. 339-356. [cited by applicant]
Zhang et al., A Feature-enriched Completely Blind Image Quality Evaluator, Institute of Electrical and Electronics Engineers Transactions on Image Processing, vol. 24, No. 8, Apr. 24, 2015, pp. 1-13. [cited by applicant]
Zhang et al., Adding Conditional Control to Text-to-image Diffusion Models, In Proceedings of the Institute of Electrical and Electronics Engineers/CVF International Conference on Computer Vision, 2023, pp. 3836-3847. [cited by applicant]
Zhang et al., Neural Light Transport for Relighting and View Synthesis, Association for Computing Machinery Transactions on Graphics, vol. 40, No. 1, Dec. 2020, 16 pages. [cited by applicant]
Zhang et al., Neural Video Portrait Relighting in Real-time via Consistency Modeling, In Proceedings of the Institute of Electrical and Electronics Engineers/CVF International Conference on Computer Vision 2021, 2021, p… [cited by applicant]
Zhang et al., Portrait Shadow Manipulation, Association for Computing Machinery Transactions on Graphics, vol. 39, No. 4, Jul. 2020, pp. 78-1:78-14. [cited by applicant]
Zhang et al., The Unreasonable Effectiveness of Deep Features as a Perceptual Metric, In Proceedings of the Institute of Electrical and Electronics Engineers Conference on Computer Vision and Pattern Recognition, Jan. 1… [cited by applicant]
Zhou et al., CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis, Available online at: https://arxiv.org/abs/2110.09788, Oct. 19, 2021, pp. 1-10. [cited by applicant]
Zhou et al., Deep Single-Image Portrait Relighting, Available Online at:https://openaccess.thecvf.com/content_ICCV_2019/papers/Zhou_Deep_Single-Image_Portrait_Relighting_ICCV_2019_paper.pdf, Oct. 27, 2019, pp. 7194-7202. [cited by applicant]