Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
skip to main content
research-article

Projective Sampling for Differentiable Rendering of Geometry

Published: 05 December 2023 Publication History

Abstract

Discontinuous visibility changes at object boundaries remain a persistent source of difficulty in the area of differentiable rendering. Left untreated, they bias computed gradients so severely that even basic optimization tasks fail.
Prior path-space methods addressed this bias by decoupling boundaries from the interior, allowing each part to be handled using specialized Monte Carlo sampling strategies. While conceptually powerful, the full potential of this idea remains unrealized since existing methods often fail to adequately sample the boundary proportional to its contribution.
This paper presents theoretical and algorithmic contributions. On the theoretical side, we transform the boundary derivative into a remarkably simple local integral that invites present and future developments.
Building on this result, we propose a new strategy that projects ordinary samples produced during forward rendering onto nearby boundaries. The resulting projections establish a variance-reducing guiding distribution that accelerates convergence of the subsequent differential phase.
We demonstrate the superior efficiency and versatility of our method across a variety of shape representations, including triangle meshes, implicitly defined surfaces, and cylindrical fibers based on Bézier curves.

Supplementary Material

ZIP File (papers_711s4-file4.zip)
supplemental
MP4 File (papers_711s4-file3.mp4)
supplemental

References

[1]
Sai Praveen Bangaru, Michaël Gharbi, Fujun Luan, Tzu-Mao Li, Kalyan Sunkavalli, Milos Hasan, Sai Bi, Zexiang Xu, Gilbert Bernstein, and Fredo Durand. 2022. Differentiable rendering of neural sdfs through reparameterization. In SIGGRAPH Asia 2022 Conference Papers. 1--9.
[2]
Sai Praveen Bangaru, Tzu-Mao Li, and Frédo Durand. 2020. Unbiased warped-area sampling for differentiable rendering. ACM Trans. Graph. 39, 6 (2020), 1--18.
[3]
Sai Praveen Bangaru, Jesse Michel, Kevin Mu, Gilbert Bernstein, Tzu-Mao Li, and Jonathan Ragan-Kelley. 2021. Systematically differentiating parametric discontinuities. ACM Trans. Graph. 40, 4 (2021), 1--18.
[4]
Thomas Booth. 2007. Unbiased Monte Carlo Estimation of the Reciprocal of an Integral. Nuclear Science and Engineering 156 (07 2007), 403--407.
[5]
David Bremer and John F. Hughes. 1998. Rapid Approximate Silhouette Rendering of Implicit Surfaces. In Proceesings of Implicit Surfaces 98.
[6]
Forrester Cole, Kyle Genova, Avneesh Sud, Daniel Vlasic, and Zhoutong Zhang. 2021. Differentiable surface rendering via non-differentiable sampling. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 6088--6097.
[7]
Andreas Griewank and Andrea Walther. 2008. Evaluating derivatives: principles and techniques of algorithmic differentiation. Vol. 105. SIAM.
[8]
Wenzel Jakob, Sébastien Speierer, Nicolas Roussel, Merlin Nimier-David, Delio Vicini, Tizian Zeltner, Baptiste Nicolet, Miguel Crespo, Vincent Leroy, and Ziyi Zhang. 2022b. Mitsuba 3 renderer. https://mitsuba-renderer.org.
[9]
Wenzel Jakob, Sébastien Speierer, Nicolas Roussel, and Delio Vicini. 2022a. Dr.Jit: A Just-In-Time Compiler for Differentiable Rendering. Transactions on Graphics (Proceedings of SIGGRAPH) 41, 4 (July 2022).
[10]
Hiroharu Kato, Yoshitaka Ushiku, and Tatsuya Harada. 2018. Neural 3D Mesh Renderer. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[11]
Samuli Laine, Janne Hellsten, Tero Karras, Yeongho Seol, Jaakko Lehtinen, and Timo Aila. 2020. Modular Primitives for High-Performance Differentiable Rendering. Transactions on Graphics (Proceedings of SIGGRAPH) 39, 6 (2020).
[12]
Tzu-Mao Li, Miika Aittala, Frédo Durand, and Jaakko Lehtinen. 2018. Differentiable monte carlo ray tracing through edge sampling. ACM Trans. Graph. 37, 6 (2018), 1--11.
[13]
Tzu-Mao Li, Michal Lukáč, Michaël Gharbi, and Jonathan Ragan-Kelley. 2020. Differentiable Vector Graphics Rasterization for Editing and Learning. ACM Trans. Graph. 39, 6 (nov 2020).
[14]
Shichen Liu, Tianye Li, Weikai Chen, and Hao Li. 2019. Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning. The IEEE International Conference on Computer Vision (ICCV) (Oct. 2019).
[15]
Matthew M. Loper and Michael J. Black. 2014. OpenDR: An Approximate Differentiable Renderer. In European Conference on Computer Vision (ECCV). Springer, 154--169.
[16]
Guillaume Loubet, Nicolas Holzschuch, and Wenzel Jakob. 2019. Reparameterizing discontinuous integrands for differentiable rendering. ACM Trans. Graph. 38, 6 (2019), 1--14.
[17]
Baptiste Nicolet, Alec Jacobson, and Wenzel Jakob. 2021. Large Steps in Inverse Rendering of Geometry. ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia) 40, 6 (Dec. 2021).
[18]
Merlin Nimier-David, Sébastien Speierer, Benoît Ruiz, and Wenzel Jakob. 2020. Radiative Backpropagation: An Adjoint Method for Lightning-Fast Differentiable Rendering. Transactions on Graphics (Proceedings of SIGGRAPH) 39, 4 (July 2020).
[19]
Marios Papas, Thomas Houit, Derek Nowrouzezahrai, Markus Gross, and Wojciech Jarosz. 2012. The Magic Lens: Refractive Steganography. ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia) 31, 6 (Nov. 2012).
[20]
Felix Petersen, Bastian Goldluecke, Christian Borgelt, and Oliver Deussen. 2022. GenDR: A Generalized Differentiable Renderer. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 4002--4011.
[21]
Osborne Reynolds. 1903. The sub-mechanics of the universe. Vol. 3. University Press.
[22]
Herman Hansson Söderlund, Alex Evans, and Tomas Akenine-Möller. 2022. Ray Tracing of Signed Distance Function Grids. Journal of Computer Graphics Techniques Vol 11, 3 (2022).
[23]
T. S. Trowbridge and K. P. Reitz. 1975. Average irregularity representation of a rough surface for ray reflection. J. Opt. Soc. Am. 65, 5 (May 1975), 531--536.
[24]
Eric Veach. 1997. Robust Monte Carlo Methods for Light Transport Simulation. Ph. D. Dissertation. Stanford University.
[25]
Eric Veach and Leonidas J. Guibas. 1995. Optimally Combining Sampling Techniques for Monte Carlo Rendering. In Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques. Association for Computing Machinery.
[26]
Delio Vicini, Sébastien Speierer, and Wenzel Jakob. 2021. Path Replay Backpropagation: Differentiating Light Paths using Constant Memory and Linear Time. Transactions on Graphics (Proceedings of SIGGRAPH) 40, 4 (Aug. 2021).
[27]
Delio Vicini, Sébastien Speierer, and Wenzel Jakob. 2022. Differentiable Signed Distance Function Rendering. Transactions on Graphics (Proceedings of SIGGRAPH) 41, 4 (July 2022).
[28]
Kai Yan, Christoph Lassner, Brian Budge, Zhao Dong, and Shuang Zhao. 2022. Efficient estimation of boundary integrals for path-space differentiable rendering. ACM Trans. Graph. 41, 4 (2022), 1--13.
[29]
Yuting Yang, Connelly Barnes, Andrew Adams, and Adam Finkelstein. 2022. A Δ: autodiff for discontinuous programs-applied to shaders. ACM Trans. Graph. 41, 4 (2022), 1--24.
[30]
Cheng Zhang, Bailey Miller, Kan Yan, Ioannis Gkioulekas, and Shuang Zhao. 2020. Path-space differentiable rendering. ACM Transactions on Graphics 39, 4 (2020).
[31]
Yang Zhou, Lifan Wu, Ravi Ramamoorthi, and Ling-Qi Yan. 2021. Vectorization for Fast, Analytic, and Differentiable Visibility. ACM Transactions on Graphics 40, 3 (July 2021).

Cited By

View all
  • (2024)A Brief Review on Differentiable Rendering: Recent Advances and ChallengesElectronics10.3390/electronics1317354613:17(3546)Online publication date: 6-Sep-2024
  • (2024)Digitizing translucent object appearance by validating computed optical propertiesApplied Optics10.1364/AO.52197463:16(4317)Online publication date: 22-May-2024
  • (2024)Conditional Mixture Path Guiding for Differentiable RenderingACM Transactions on Graphics10.1145/365813343:4(1-11)Online publication date: 19-Jul-2024
  • Show More Cited By

Index Terms

  1. Projective Sampling for Differentiable Rendering of Geometry

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Transactions on Graphics
    ACM Transactions on Graphics  Volume 42, Issue 6
    December 2023
    1565 pages
    ISSN:0730-0301
    EISSN:1557-7368
    DOI:10.1145/3632123
    Issue’s Table of Contents
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 05 December 2023
    Published in TOG Volume 42, Issue 6

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. differentiable rendering
    2. geometry reconstruction

    Qualifiers

    • Research-article

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)336
    • Downloads (Last 6 weeks)37
    Reflects downloads up to 10 Nov 2024

    Other Metrics

    Citations

    Cited By

    View all
    • (2024)A Brief Review on Differentiable Rendering: Recent Advances and ChallengesElectronics10.3390/electronics1317354613:17(3546)Online publication date: 6-Sep-2024
    • (2024)Digitizing translucent object appearance by validating computed optical propertiesApplied Optics10.1364/AO.52197463:16(4317)Online publication date: 22-May-2024
    • (2024)Conditional Mixture Path Guiding for Differentiable RenderingACM Transactions on Graphics10.1145/365813343:4(1-11)Online publication date: 19-Jul-2024
    • (2024)Path-Space Differentiable Rendering of Implicit SurfacesACM SIGGRAPH 2024 Conference Papers10.1145/3641519.3657473(1-11)Online publication date: 13-Jul-2024
    • (2024)Fabricable 3D Wire ArtACM SIGGRAPH 2024 Conference Papers10.1145/3641519.3657453(1-11)Online publication date: 13-Jul-2024
    • (2024)Media2Face: Co-speech Facial Animation Generation With Multi-Modality GuidanceACM SIGGRAPH 2024 Conference Papers10.1145/3641519.3657413(1-13)Online publication date: 13-Jul-2024
    • (2024)CNS-Edit: 3D Shape Editing via Coupled Neural Shape OptimizationACM SIGGRAPH 2024 Conference Papers10.1145/3641519.3657412(1-12)Online publication date: 13-Jul-2024
    • (2024)Aperture-Aware Lens DesignACM SIGGRAPH 2024 Conference Papers10.1145/3641519.3657398(1-10)Online publication date: 13-Jul-2024
    • (2024)A Persona-Infused Cross-Task Graph Network for Multimodal Emotion Recognition with Emotion Shift Detection in ConversationsProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3626772.3657944(2266-2270)Online publication date: 10-Jul-2024
    • (2024)ArabicaQA: A Comprehensive Dataset for Arabic Question AnsweringProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3626772.3657889(2049-2059)Online publication date: 10-Jul-2024
    • Show More Cited By

    View Options

    Get Access

    Login options

    Full Access

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media