pith. sign in

arxiv: 2606.00137 · v1 · pith:QUTNUNTUnew · submitted 2026-05-28 · 💻 cs.CV · cs.GR

Advances in Neural 3D Mesh Texturing: A Survey

Sai Raj Kishore Perla , Hao Zhang , Ali Mahdavi-Amiri This is my paper

Pith reviewed 2026-06-29 07:27 UTC · model grok-4.3

classification 💻 cs.CV cs.GR
keywords neural 3D mesh texturingtexture synthesistexture transfertexture completionGANdiffusion modelssurveytaxonomy
0
0 comments X

The pith

A survey organizes neural 3D mesh texturing methods into a unified taxonomy from GAN-based to diffusion-based pipelines.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper sets out a structured review of neural methods for adding textures to 3D meshes, a step that determines visual realism in objects used across modeling, animation, and gaming. It begins by covering basic elements such as mesh geometry, texture mapping, differentiable rendering, and neural generative models. The central effort then groups existing work on texture synthesis, transfer, and completion into one taxonomy that follows the shift from early GAN techniques to current diffusion pipelines. The review also examines architectures, supervision choices, datasets, evaluation methods, applications, and remaining problems. A reader would care because meshes stay the dominant format in production pipelines, so a clear map of the neural texturing literature can guide both research and practical development.

Core claim

The authors claim to deliver a comprehensive review by summarizing foundations in mesh geometry, texture mapping, differentiable rendering, and neural generative models, then organizing the literature on neural 3D mesh texturing into a unified taxonomy that spans early GAN-based methods to modern diffusion-based pipelines, while further analyzing common architectures and supervision strategies, reviewing datasets and evaluation protocols, and discussing emerging applications, practical systems, and open challenges.

What carries the argument

The unified taxonomy that spans early GAN-based methods to modern diffusion-based pipelines and groups techniques for texture synthesis, transfer, and completion.

If this is right

  • New methods can be placed inside the taxonomy to show how they extend prior GAN or diffusion approaches.
  • Identified patterns in architectures and supervision can be reused to design improved training for texturing tasks.
  • The compiled datasets and evaluation protocols can function as standard benchmarks for future techniques.
  • The listed open challenges can focus research on gaps that affect commercial 3D asset pipelines.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The taxonomy could be checked for durability by testing whether papers published after the survey still map cleanly into its categories.
  • Connections between the mesh-texturing taxonomy and parallel work on other 3D representations might reveal opportunities for cross-field technique transfer.

Load-bearing premise

The assumption that the selected papers and the proposed taxonomy give representative and unbiased coverage of the entire research area.

What would settle it

Identification of a sizable collection of neural 3D mesh texturing papers that do not fit any category in the taxonomy or were omitted from the review.

Figures

Figures reproduced from arXiv: 2606.00137 by Ali Mahdavi-Amiri, Hao Zhang, Sai Raj Kishore Perla.

Figure 1
Figure 1. Figure 1: Neural 3D Mesh Texturing spans diverse settings, with works addressing different aspects of surface appearance genera￾tion and control. For instance, (a) Texture Alignment, learning class-consistent UV mappings [CYF22]; (b) Texturing Humans and Gar￾ments [ZWC∗ 24], also demonstrating texture synthesis from an input image; (c) Texture Variation and Transfer [MEM24], also illustrating texturing from an input… view at source ↗
Figure 2
Figure 2. Figure 2: A 3D mesh is defined by vertices (points), edges (line segments), and faces (surface elements, often triangles or quads), which combine into surface patches that approximate the object’s geometry. Figure reproduced from [Lob09] [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: 3D shape representations. Voxels discretize space, point clouds sample points, meshes encode surface connectivity, and SDFs represent shapes implicitly via a continuous signed distance function. Figure reproduced from [AFL23]. damentals of 3D mesh representation in Sec. 2.1, introduce surface parameterization as a bridge from 3D surfaces to 2D texture do￾mains in Sec. 2.2, summarize rendering and different… view at source ↗
Figure 5
Figure 5. Figure 5: Differentiable rendering enables backpropagation of image-space losses through the rendering pipeline (occlusion, shading, light transport, and projection) to optimize scene param￾eters (geometry, materials, lighting, and viewpoint). Figure repro￾duced from [BN25]. representation and learning, and refer readers to dedicated surveys for a comprehensive overview [SPR06,HPS08,FH05]. 2.3. Differentiable Mesh R… view at source ↗
Figure 6
Figure 6. Figure 6: Representative PBR materials rendered under identical geometry and lighting. Varying material map parameters (e.g., base color/albedo, roughness, metallic, normals, and emissive terms) yield distinct, relightable appearances such as leather, cloth, ce￾ramic, wood, marble, microfiber, and chromium, illustrating how PBR materials extend beyond a single RGB texture. Figure repro￾duced from [wol16]. 2.4. Physi… view at source ↗
Figure 7
Figure 7. Figure 7: An overview of Neural Radiance Fields (NeRFs). Images are synthesized by sampling 5D coordinates—3D position (x, y,z) and viewing direction (θ,φ)—along camera rays (a) and feeding them to a neural network that outputs color (R,G,B) and volume density σ (b). Figure adapted from [MST∗ 20] [PITH_FULL_IMAGE:figures/full_fig_p006_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: CLIP jointly trains image and text encoders using a contrastive loss to match paired images and texts within a batch. Figure adapted from [R ∗ 21]. where σ denotes volume density and c the view-dependent color ( [PITH_FULL_IMAGE:figures/full_fig_p006_8.png] view at source ↗
Figure 10
Figure 10. Figure 10: An overview of generative adversarial networks (GANs). A generator G maps noise samples (latent codes) to syn￾thetic images, while a discriminator D learns to distinguish real images from generated ones; both are trained adversarially using LGAN (see Sec. 2.5.4). Figure reproduced from [CCC∗ 20]. 2.5.4. Generative Adversarial Networks Generative adversarial networks (GANs) formulate generative modeling as… view at source ↗
Figure 13
Figure 13. Figure 13: Unconditional texture generation with Texturify. The model learns a distribution of plausible textures conditioned on 3D shape from real-image supervision, and infers diverse texture pro￾posals for a given input shape. Figure reproduced from [STM∗ 22]. 3.2.1. Unconditional Texture Generation Unconditional texture generation produces textures without explicit stylistic guidance, instead sampling appearance… view at source ↗
Figure 12
Figure 12. Figure 12: Depth vs. edges for structural guidance. Depth maps are typically smooth and provide coarse structural cues. In con￾trast, geometric edges derived from mesh attributes (e.g., nor￾mals, depth discontinuities, and connectivity) are more detailed and aligned with mesh geometry, improving mesh–texture consistency. Figure reproduced from [PWMAZ24]. 3.1. Structural Guidance Structural guidance provides geometri… view at source ↗
Figure 14
Figure 14. Figure 14: Text-conditioned texture generation. Given untextured meshes (left), Text2Tex synthesizes textures guided by text prompts (right). Figure reproduced from [CSL∗ 23]. Text-based Generation. Using natural language as guidance is one of the most popular and convenient ways to control 3D tex￾ture synthesis, owing to the accessibility of text as an interface. In text-guided texturing, a user provides a descript… view at source ↗
Figure 16
Figure 16. Figure 16: Training pipeline of Texturify. Given an untex￾tured input mesh, a surface-feature encoder and a StyleGAN2- based [KLA∗ 20] generator predict a texture for the mesh. The tex￾tured mesh is then differentiably rendered, and the resulting images are evaluated by two discriminators (a global discriminator DI and a patch-based discriminator DP) against real images; the adversar￾ial loss trains all networks. Fi… view at source ↗
Figure 17
Figure 17. Figure 17: An overview of Paint-It. Given an untextured mesh and a text prompt, the method optimizes PBR texture maps (e.g., albedo, roughness, metalness, normals) using SDS guidance [PJBM23] from a frozen text-to-image diffusion model over multi-view ren￾derings. Figure reproduced from [YJPMO24]. troduces diversity and reduces bias in score estimation. As a result, VSD can yield sharper and more diverse details tha… view at source ↗
Figure 18
Figure 18. Figure 18: Given a text prompt, 3D Paintbrush predicts both the target region and corresponding texture on the in￾put mesh, enabling spatially controlled texturing. Figure adapted from [DLAH24]. in a single pass, these methods typically require many optimiza￾tion and denoising steps per shape. Even with accelerations such as latent-space distillation/optimization [MRP∗ 23] or efficient dif￾ferentiable rendering [LHK… view at source ↗
Figure 20
Figure 20. Figure 20: An overview of a synchronized multi-view texturing pipeline. Per-view diffusion denoising is coupled through a Blend module that fuses per-view textures into a shared texture image, im￾proving cross-view consistency. Figure reproduced from [ZPZ∗ 24]. parallelizing view synthesis, such methods can reduce runtime and improve consistency, since texture evolves jointly across views and overlapping boundary re… view at source ↗
Figure 21
Figure 21. Figure 21: A feed-forward texturing pipeline (TEXGen). A diffu￾sion U-Net denoises a latent UV texture atlas conditioned on ras￾terized mesh cues and text embeddings to generate a UV texture map in a single pass. Figure reproduced from [YYG∗ 24]. adopts a coarse-to-fine design that first diffuses appearance in sur￾face point space to obtain a globally consistent prior, then projects it into UV space and refines a hi… view at source ↗
Figure 22
Figure 22. Figure 22: Part-aware human texturing. Given a single in￾put image (left), the method segments a textureless human mesh into semantic parts and textures them to produce a detailed 3D human with clean region boundaries (right). Figure adapted from [NKML25]. they extract a partial texture from visible pixels, render a full-body image, and use a pretrained re-ID CNN to compare this render with the real image. The textu… view at source ↗
Figure 23
Figure 23. Figure 23: Objaverse-XL provides over 10M 3D objects spanning diverse categories, enabling large-scale training and benchmark￾ing for mesh texturing. Figure reproduced from [D ∗ 23]. dataset [CDF∗ 17] provides 90 real indoor scenes with RGB￾D captures, surface reconstructions, and textured meshes, making it a valuable resource for methods that leverage scene-level geometry and appearance. Some synthetic datasets foc… view at source ↗
Figure 24
Figure 24. Figure 24: Applications of 3D mesh texturing in games and VFX. Textures add material detail and realism to production assets such as game characters (left) and digital humans (right). Figure adapted from [Dem24,Wol17]. broadly, diversified textures on scene meshes are often used in simulation to improve sim-to-real transfer for perception and control in robotics [TFR∗ 17]. • Digital humans and telepresence. Neural t… view at source ↗
read the original abstract

Texturing 3D meshes plays a vital role in determining the visual realism of digital objects and scenes. Although recent generative 3D approaches based on Neural Radiance Fields and Gaussian Splatting can produce textured assets directly, polygonal meshes remain the core representation across modeling, animation, visual effects, and gaming pipelines. Neural 3D mesh texturing therefore continues to be an essential and active area of research. In this survey, we present a comprehensive review of recent advances in neural 3D mesh texturing, covering methods for texture synthesis, transfer, and completion. We first summarize key foundations in mesh geometry, texture mapping, differentiable rendering, and neural generative models, and then organize the literature into a unified taxonomy spanning early GAN-based methods to modern diffusion-based pipelines. We further analyze common architectures and supervision strategies, review datasets and evaluation protocols, and discuss emerging applications, practical/commercial systems, and open challenges. Together, these insights provide a structured perspective on the current landscape and help guide future developments in learning-based 3D mesh texturing.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper claims to deliver a comprehensive review of recent advances in neural 3D mesh texturing, covering texture synthesis, transfer, and completion. It summarizes foundations in mesh geometry, texture mapping, differentiable rendering, and neural generative models, then organizes the literature into a unified taxonomy spanning early GAN-based methods to modern diffusion-based pipelines. It further analyzes architectures and supervision strategies, reviews datasets and evaluation protocols, and discusses applications, commercial systems, and open challenges.

Significance. If the taxonomy proves representative, the survey would provide a useful structured overview of an active subfield, helping researchers identify trends from GAN-based to diffusion-based approaches and highlighting open challenges. The explicit attempt to unify disparate methods under one taxonomy is a constructive contribution for the computer vision community.

major comments (1)
  1. [Abstract] Abstract: the central claim that the work presents a 'comprehensive review' and 'unified taxonomy' spanning GAN-based to diffusion-based methods rests on an unstated paper selection process. No search protocol, inclusion/exclusion criteria, databases, date range, or screened-vs-retained counts are described, making it impossible to verify that the taxonomy is exhaustive or free of selection bias.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on our survey. The concern regarding the lack of an explicit paper selection protocol is valid and directly impacts the verifiability of our claims of comprehensiveness. We will revise the manuscript to include a dedicated methodology section describing our literature search process, thereby addressing this point without altering the taxonomy or core analysis.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim that the work presents a 'comprehensive review' and 'unified taxonomy' spanning GAN-based to diffusion-based methods rests on an unstated paper selection process. No search protocol, inclusion/exclusion criteria, databases, date range, or screened-vs-retained counts are described, making it impossible to verify that the taxonomy is exhaustive or free of selection bias.

    Authors: We agree that transparency in the paper selection process is necessary for a survey to substantiate claims of comprehensiveness and to allow assessment of potential selection bias. In the revised version, we will insert a new subsection (e.g., Section 2.1 'Literature Review Methodology') that explicitly states: (1) the databases and repositories searched (Google Scholar, arXiv, major CV conferences 2014–2024), (2) the keyword combinations employed, (3) inclusion criteria (peer-reviewed or preprint works focused on neural mesh texturing with GANs, VAEs, or diffusion models) and exclusion criteria (pure geometry papers, non-neural methods, or works outside the date range), and (4) approximate counts of papers screened versus retained. This addition will be placed early in the manuscript so that the taxonomy can be evaluated in context. The taxonomy itself and the reviewed methods will remain unchanged. revision: yes

Circularity Check

0 steps flagged

No circularity: survey paper with no derivations or predictions

full rationale

This manuscript is a literature survey that summarizes foundations in mesh geometry and neural models, then organizes prior work into a taxonomy spanning GAN-based to diffusion-based methods. No equations, fitted parameters, predictions, or first-principles derivations appear anywhere in the provided text or abstract. The central claim of providing a 'unified taxonomy' is a descriptive organization of external literature rather than a result derived from internal inputs; it therefore cannot reduce to itself by construction. No self-citation chains, ansatzes, or renamings of known results are load-bearing in any derivation sense. The paper is self-contained as a review and receives the default non-finding score.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a survey paper the contribution is organizational. No free parameters, mathematical axioms, or new invented entities are introduced by the authors.

pith-pipeline@v0.9.1-grok · 5718 in / 1124 out tokens · 31178 ms · 2026-06-29T07:27:47.894108+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

300 extracted references · 15 canonical work pages · 4 internal anchors

  1. [1]

    J. M. Buhmann and D. W. Fellner and M. Held and J. Ketterer and J. Puzicha , TITLE =. 1998 , PAGES =. doi:10.1111/1467-8659.00269 , NOTE =

    work page doi:10.1111/1467-8659.00269 1998

  2. [2]

    and Helmberg, Christoph , TITLE =

    Fellner, Dieter W. and Helmberg, Christoph , TITLE =. 1993 , PAGES =

    1993

  3. [3]

    Kobbelt and M

    L. Kobbelt and M. Stamminger and H.-P. Seidel , title =. doi:10.1111/1467-8659.16.3conferenceissue.36 , note =

    work page doi:10.1111/1467-8659.16.3conferenceissue.36

  4. [4]

    Lafortune and Sing-Choong Foo and Kenneth E

    Eric P. Lafortune and Sing-Choong Foo and Kenneth E. Torrance and Donald P. Greenberg , title =. Proc. SIGGRAPH '97 , volume = 31, pages =

  5. [5]

    2010 , doi =

    Botsch, Mario and Kobbelt, Leif and Pauly, Mark and Alliez, Pierre and L. 2010 , doi =

    2010

  6. [6]

    , title =

    Garland, Michael and Heckbert, Paul S. , title =. Proceedings of SIGGRAPH , year =

  7. [7]

    Proceedings of SIGGRAPH , year =

    Hoppe, Hugues , title =. Proceedings of SIGGRAPH , year =

  8. [8]

    Proceedings of SIGGRAPH , year =

    Stam, Jos , title =. Proceedings of SIGGRAPH , year =

  9. [9]

    Computer Graphics Forum , year =

    Shamir, Ariel , title =. Computer Graphics Forum , year =

  10. [10]

    Proceedings of SIGGRAPH , year =

    Pfister, Hanspeter and Zwicker, Matthias and Van Baar, Jeroen and Gross, Markus , title =. Proceedings of SIGGRAPH , year =

  11. [11]

    Proceedings of SIGGRAPH , year =

    Rusinkiewicz, Szymon and Levoy, Marc , title =. Proceedings of SIGGRAPH , year =

  12. [12]

    and Xu, Danfei and Gwak, JunYoung and Chen, Kevin and Savarese, Silvio , title =

    Choy, Christopher B. and Xu, Danfei and Gwak, JunYoung and Chen, Kevin and Savarese, Silvio , title =. European Conference on Computer Vision , year =

  13. [13]

    and Cline, Harvey E

    Lorensen, William E. and Cline, Harvey E. , title =. 1987 , volume =. doi:10.1145/37402.37422 , journal =

    work page doi:10.1145/37402.37422 1987

  14. [14]

    ACM Transactions on Graphics , year =

    Kerbl, Bernhard and Kopanas, Georgios and Leimk. ACM Transactions on Graphics , year =

  15. [15]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , year =

    Koch, Sebastian and Matveev, Albert and Jiang, Zhongshi and Williams, Francis and Artemov, Alexey and Burnaev, Evgeny and Alexa, Marc and Zorin, Denis and Panozzo, Daniele , title =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , year =

  16. [16]

    Proceedings of SIGGRAPH , year =

    Taubin, Gabriel , title =. Proceedings of SIGGRAPH , year =

  17. [17]

    Proceedings of SIGGRAPH , year =

    Desbrun, Mathieu and Meyer, Mark and Schr. Proceedings of SIGGRAPH , year =

  18. [18]

    Proceedings of SIGGRAPH , year =

    Alliez, Pierre and Meyer, Mark and Desbrun, Mathieu , title =. Proceedings of SIGGRAPH , year =

  19. [19]

    Proceedings of SIGGRAPH , year =

    Ju, Tao , title =. Proceedings of SIGGRAPH , year =

  20. [20]

    Eurographics Symposium on Geometry Processing (SGP) , year =

    Kazhdan, Michael and Bolitho, Matthew and Hoppe, Hugues , title =. Eurographics Symposium on Geometry Processing (SGP) , year =

  21. [21]

    Computer-Aided Design , year =

    Catmull, Edwin and Clark, James , title =. Computer-Aided Design , year =

  22. [22]

    Foundations and Trends in Computer Graphics and Vision , year =

    Sheffer, Alla and Praun, Emil and Rose, Kenneth , title =. Foundations and Trends in Computer Graphics and Vision , year =

  23. [23]

    and Snyder, John and Gortler, Steven J

    Sander, Pedro V. and Snyder, John and Gortler, Steven J. and Hoppe, Hugues , title =. Proceedings of ACM SIGGRAPH 2001 , year =

    2001

  24. [24]

    Proceedings of ACM SIGGRAPH 1983 , year =

    Williams, Lance , title =. Proceedings of ACM SIGGRAPH 1983 , year =

    1983

  25. [25]

    and Sander, Pedro V

    Y\"uksel, Cem and Kaldor, Jonathan M. and Sander, Pedro V. and Hoppe, Hugues , title =. Computer Graphics Forum , year =

  26. [26]

    Computer Graphics Forum (Proc

    Burley, Brent and Lacewell, Dylan , title =. Computer Graphics Forum (Proc. EGSR) , year =

  27. [27]

    ACM Transactions on Graphics , year =

    L\'evy, Bruno and Petitjean, Sylvain and Ray, Nicolas and Maillot, J\'er\^ome , title =. ACM Transactions on Graphics , year =

  28. [28]

    ACM Transactions on Graphics , year =

    Sheffer, Alla and L\'evy, Bruno and Mogilnitsky, Maxim and Bogomyakov, Alexander , title =. ACM Transactions on Graphics , year =

  29. [29]

    Computer Graphics Forum , year =

    Mullen, Patrick and Tong, Yiying and Alliez, Pierre and Desbrun, Mathieu , title =. Computer Graphics Forum , year =

  30. [30]

    ACM Transactions on Graphics , year =

    Sawhney, Rohan and Crane, Keenan , title =. ACM Transactions on Graphics , year =

  31. [31]

    ACM Transactions on Graphics , year =

    Smith, Jason and Schaefer, Scott , title =. ACM Transactions on Graphics , year =

  32. [32]

    ACM Transactions on Graphics , year =

    Lipman, Yaron , title =. ACM Transactions on Graphics , year =

  33. [33]

    and Aigerman, Noam and Basri, Ronen and Lipman, Yaron , title =

    Kovalsky, Shahar Z. and Aigerman, Noam and Basri, Ronen and Lipman, Yaron , title =. ACM Transactions on Graphics , year =

  34. [34]

    Proceedings of the ACM Symposium on Interactive 3D Graphics and Games , year =

    Poranne, Roi and Vaisset, Maxime and O'Sullivan, Fearghal and Baran, Ilya and Sorkine-Hornung, Olga and Jacobson, Alec , title =. Proceedings of the ACM Symposium on Interactive 3D Graphics and Games , year =

  35. [35]

    ACM Transactions on Graphics , year =

    L\'evy, Bruno and Li, Wenchao and Chen, Yang and Panozzo, Daniele and Bommes, David and Jakob, Wenzel and Sorkine-Hornung, Olga and Sheffer, Alla , title =. ACM Transactions on Graphics , year =

  36. [36]

    and Chaudhuri, Siddhartha and Saito, Jun and Groueix, Thibault , title =

    Aigerman, Noam and Gupta, Kunal and Kim, Vladimir G. and Chaudhuri, Siddhartha and Saito, Jun and Groueix, Thibault , title =. ACM Transactions on Graphics , year =

  37. [37]

    European Conference on Computer Vision , year =

    Low, Weng Fei and Lee, Gim Hee , title =. European Conference on Computer Vision , year =

  38. [38]

    and Hanocka, Rana , title =

    Liu, Richard and Aigerman, Noam and Kim, Vladimir G. and Hanocka, Rana , title =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , year =

  39. [39]

    and Igarashi, Takeo and Grinspun, Eitan , title =

    Umetani, Nobuyuki and Kaufman, Danny M. and Igarashi, Takeo and Grinspun, Eitan , title =. ACM Transactions on Graphics , year =

  40. [40]

    ACM Transactions on Graphics , year =

    Pietroni, Nico and Dumery, Corentin and Gu\'enot-Falque, Rapha\"el and Liu, Mark and Vidal-Calleja, Teresa and Sorkine-Hornung, Olga , title =. ACM Transactions on Graphics , year =

  41. [41]

    , title =

    Kajiya, James T. , title =. ACM SIGGRAPH Computer Graphics , year =

  42. [42]

    2023 , isbn =

    Pharr, Matt and Jakob, Wenzel and Humphreys, Greg , title =. 2023 , isbn =

    2023

  43. [43]

    Proceedings of SIGGRAPH , year =

    Debevec, Paul , title =. Proceedings of SIGGRAPH , year =

  44. [44]

    and Bigler, James and Dietrich, Andreas and others , title =

    Parker, Steven G. and Bigler, James and Dietrich, Andreas and others , title =. ACM Transactions on Graphics (Proceedings of SIGGRAPH) , year =

  45. [45]

    , title =

    Loper, Matthew and Black, Michael J. , title =. European Conference on Computer Vision , year =

  46. [46]

    2018 , pages =

    Kato, Hiroharu and Ushiku, Yoshitaka and Harada, Tatsuya , booktitle =. 2018 , pages =

    2018

  47. [47]

    Proceedings of the IEEE/CVF International Conference on Computer Vision , year =

    Liu, Shichen and Li, Weikai and Chen, Weiyue and Li, Xiaowei , title =. Proceedings of the IEEE/CVF International Conference on Computer Vision , year =

  48. [48]

    and Lehtinen, Jaakko and Jacobson, Alec and Fidler, Sanja , title =

    Chen, Wenzheng and Gao, Jun and Ling, Huan and Smith, Edward J. and Lehtinen, Jaakko and Jacobson, Alec and Fidler, Sanja , title =. Advances in Neural Information Processing Systems , url =

  49. [49]

    Advances in Neural Information Processing Systems , year =

    Chen, Wenzheng and Litalien, Joey and Gao, Jun and Wang, Zian and Tsang, Clement Fuji and Khamis, Sameh and Litany, Or and Fidler, Sanja , title =. Advances in Neural Information Processing Systems , year =

  50. [50]

    ACM Transactions on Graphics , year =

    Li, Tzu-Mao and Aittala, Miika and Durand, Fr. ACM Transactions on Graphics , year =

  51. [51]

    ACM Transactions on Graphics , year =

    Loubet, Guillaume and Holzschuch, Nicolas and Jakob, Wenzel , title =. ACM Transactions on Graphics , year =

  52. [52]

    ACM Transactions on Graphics , year =

    Zhang, Cheng and Miller, Bailey and Yan, Kai and Gkioulekas, Ioannis and Zhao, Shuang , title =. ACM Transactions on Graphics , year =

  53. [53]

    ACM Transactions on Graphics , year =

    Nimier-David, Merlin and Vicini, Delio and Zeltner, Tizian and Jakob, Wenzel , title =. ACM Transactions on Graphics , year =

  54. [54]

    ACM Transactions on Graphics , year =

    Jakob, Wenzel and Speierer, S. ACM Transactions on Graphics , year =

  55. [55]

    2020 , issue_date =

    Laine, Samuli and Hellsten, Janne and Karras, Tero and Seol, Yeongho and Lehtinen, Jaakko and Aila, Timo , title =. 2020 , issue_date =. doi:10.1145/3414685.3417861 , journal =

    work page doi:10.1145/3414685.3417861 2020

  56. [56]

    2020 , howpublished =

    Ravi, Nikhila and Reizenstein, Jeremy and Novotny, David and Gordon, Taylor and Lo, Wan-Yen and Johnson, Justin and Gkioxari, Georgia , title =. 2020 , howpublished =

    2020

  57. [57]

    2019 , howpublished =

    Jatavallabhula, Krishna Murthy and Smith, Edward and Lafleche, Jean-Francois and Tsang, Clement Fuji and Rozantsev, Artem and Chen, Wenzheng and Xiang, Tommy and Lebaredian, Rev and Fidler, Sanja , title =. 2019 , howpublished =

    2019

  58. [58]

    2018 , doi =

    Akenine. 2018 , doi =

    2018

  59. [59]

    Computer Graphics Forum , year =

    Xie, Yiheng and Takikawa, Towaki and Saito, Shunsuke and Litany, Or and Yan, Shiqin and Khan, Numair and Tombari, Federico and Tompkin, James and Sitzmann, Vincent and Sridhar, Srinath , title =. Computer Graphics Forum , year =

  60. [60]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , year =

    Mescheder, Lars and Oechsle, Michael and Niemeyer, Michael and Nowozin, Sebastian and Geiger, Andreas , title =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , year =

  61. [61]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , year =

    Park, Jeong Joon and Florence, Peter and Straub, Julian and Newcombe, Richard and Lovegrove, Steven , title =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , year =

  62. [62]

    and Bergman, Alexander W

    Sitzmann, Vincent and Martel, Julien N.P. and Bergman, Alexander W. and Lindell, David B. and Wetzstein, Gordon , title =. arXiv , year =

  63. [63]

    and Mildenhall, Ben and Fridovich-Keil, Sara and Raghavan, Nithin and Singhal, Utkarsh and Ramamoorthi, Ravi and Barron, Jonathan T

    Tancik, Matthew and Srinivasan, Pratul P. and Mildenhall, Ben and Fridovich-Keil, Sara and Raghavan, Nithin and Singhal, Utkarsh and Ramamoorthi, Ravi and Barron, Jonathan T. and Ng, Ren , title =. Advances in Neural Information Processing Systems , year =

  64. [64]

    and Tancik, Matthew and Barron, Jonathan T

    Mildenhall, Ben and Srinivasan, Pratul P. and Tancik, Matthew and Barron, Jonathan T. and Ramamoorthi, Ravi and Ng, Ren , title =. European Conference on Computer Vision , year =

  65. [65]

    and Mildenhall, Ben and Tancik, Matthew and Hedman, Peter and Martin-Brualla, Ricardo and Srinivasan, Pratul P

    Barron, Jonathan T. and Mildenhall, Ben and Tancik, Matthew and Hedman, Peter and Martin-Brualla, Ricardo and Srinivasan, Pratul P. , title =. Proceedings of the IEEE/CVF International Conference on Computer Vision , year =

  66. [66]

    ACM Transactions on Graphics , year =

    M. ACM Transactions on Graphics , year =

  67. [67]

    European Conference on Computer Vision , year =

    Chen, Anpei and Xu, Zexiang and Geiger, Andreas and Yu, Jingyi and Su, Hao , title =. European Conference on Computer Vision , year =

  68. [68]

    Advances in Neural Information Processing Systems , year =

    Yariv, Lior and Kasten, Yoni and Moran, Dror and Galun, Meirav and Atzmon, Matan and Basri, Ronen and Lipman, Yaron , title =. Advances in Neural Information Processing Systems , year =

  69. [69]

    Advances in Neural Information Processing Systems , year =

    Wang, Peng and Liu, Lingjie and Liu, Yuan and Theobalt, Christian and Komura, Taku and Wang, Wenping , title =. Advances in Neural Information Processing Systems , year =

  70. [70]

    Proceedings of the IEEE/CVF International Conference on Computer Vision , year =

    Oechsle, Michael and Peng, Songyou and Geiger, Andreas , title =. Proceedings of the IEEE/CVF International Conference on Computer Vision , year =

  71. [71]

    Proceedings of the IEEE/CVF International Conference on Computer Vision , year =

    Oechsle, Michael and Mescheder, Lars and Niemeyer, Michael and Strauss, Thilo and Geiger, Andreas , title =. Proceedings of the IEEE/CVF International Conference on Computer Vision , year =

  72. [72]

    and Ghahramani, Zoubin and Jaakkola, Tommi S

    Jordan, Michael I. and Ghahramani, Zoubin and Jaakkola, Tommi S. and Saul, Lawrence K. , title =. Machine Learning , year =

  73. [73]

    and Hinton, Geoffrey E

    Neal, Radford M. and Hinton, Geoffrey E. , title =. Learning in Graphical Models , editor =. 1998 , pages =

    1998

  74. [74]

    and Kucukelbir, Alp and McAuliffe, Jon D

    Blei, David M. and Kucukelbir, Alp and McAuliffe, Jon D. , title =. Journal of the American Statistical Association , year =

  75. [75]

    , title =

    Kullback, Solomon and Leibler, Richard A. , title =. The Annals of Mathematical Statistics , year =

  76. [76]

    and Neal, Radford M

    Dayan, Peter and Hinton, Geoffrey E. and Neal, Radford M. and Zemel, Richard S. , title =. Neural Computation , year =

  77. [77]

    and Salakhutdinov, Ruslan R

    Hinton, Geoffrey E. and Salakhutdinov, Ruslan R. , title =. Science , year =

  78. [78]

    and Welling, Max , title =

    Kingma, Diederik P. and Welling, Max , title =. 2014 , howpublished =

    2014

  79. [79]

    2014 , howpublished =

    Rezende, Danilo Jimenez and Mohamed, Shakir and Wierstra, Daan , title =. 2014 , howpublished =

    2014

  80. [80]

    2015 , howpublished =

    Rezende, Danilo and Mohamed, Shakir , title =. 2015 , howpublished =

    2015

Showing first 80 references.