Lune

SIGGRAPH2024Top-tier venue

Conditional Mixture Path Guiding for Differentiable Rendering

Zhimin Fan, Pengcheng Shi, Mufan Guo, Ruoyu Fu, Yanwen Guo, Jie Guo

Abstract

The efficiency of inverse optimization in physically based differentiable rendering heavily depends on the variance of Monte Carlo estimation. Despite recent advancements emphasizing the necessity of tailored differential sampling strategies, the general approaches remain unexplored. In this paper, we investigate the interplay between local sampling decisions and the estimation of light path derivatives. Considering that modern differentiable rendering algorithms share the same path for estimating differential radiance and ordinary radiance, we demonstrate that conventional guiding approaches, conditioned solely on the last vertex, cannot attain this density. Instead, a mixture of different sampling distributions is required, where the weights are conditioned on all the previously sampled vertices in the path. To embody our theory, we implement a conditional mixture path guiding that explicitly computes optimal weights on the fly. Furthermore, we show how to perform positivization to eliminate sign variance and extend to scenes with millions of parameters. To the best of our knowledge, this is the first generic framework for applying path guiding to differentiable rendering. Extensive experiments demonstrate that our method achieves nearly one order of magnitude improvements over state-of-the-art methods in terms of variance reduction in gradient estimation and errors of inverse optimization. The implementation of our proposed method is available at https://github.com/mollnn/conditional-mixture.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • DR.JIT: a just-in-time compiler for differentiable rendering cites Radiative backpropagation: an adjoint method for lightning-fast differentiable rendering
  • DR.JIT: a just-in-time compiler for differentiable rendering cites Path-space differentiable rendering
  • Radiance Caching for Differentiable Path Tracing cites Radiative backpropagation: an adjoint method for lightning-fast differentiable rendering
  • Robust Computation of Boundary Path Integrals Using Kernel-Density Estimation cites Path-space differentiable rendering
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. Guiding-Based Importance Sampling for Walk on StarsTianyu Huang, Jingwang Ling, Shuang Zhao, Feng XuSIGGRAPH 2025 · 6 citations
  2. Radiance Caching for Differentiable Path TracingZiyi Zhang, Delio Vicini, Sebastian Winberg, Stephan J. Garbin et al.SIGGRAPH 2026
  3. Robust Computation of Boundary Path Integrals Using Kernel-Density EstimationPeiyu Xu, Lifan Wu, Benedikt Bitterli, Ravi Ramamoorthi et al.SIGGRAPH 2026

Builds on17

  1. Spatiotemporal reservoir resampling for real-time ray tracing with dynamic direct lightingBenedikt Bitterli, Chris Wyman, Matt Pharr, Peter Shirley et al.SIGGRAPH 2020 · 168 citations
  2. DR.JIT: a just-in-time compiler for differentiable renderingWenzel Jakob, Sébastien Speierer, Nicolas Roussel, Delio ViciniSIGGRAPH 2022 · 160 citations
  3. Path-space differentiable renderingCheng Zhang, Bailey Miller, Kai Yan, Ioannis Gkioulekas et al.SIGGRAPH 2020 · 155 citations
  4. Differentiable signed distance function renderingDelio Vicini, Sébastien Speierer, Wenzel JakobSIGGRAPH 2022 · 112 citations
  5. Radiative backpropagation: an adjoint method for lightning-fast differentiable renderingMerlin Nimier-David, Sébastien Speierer, Benoît Ruiz, Wenzel JakobSIGGRAPH 2020 · 107 citations

Related papers

  1. Monte Carlo estimators for differential light transportTizian Zeltner, Sébastien Speierer, Iliyan Georgiev, Wenzel JakobSIGGRAPH 2021 · 70 citations
  2. Revisiting controlled mixture sampling for rendering applicationsQingqin Hua, Pascal Grittmann, Philipp SlusallekSIGGRAPH 2023 · 7 citations
  3. Efficient estimation of boundary integrals for path-space differentiable renderingKai Yan, Christoph Lassner, Brian Budge, Zhao Dong et al.SIGGRAPH 2022 · 34 citations
  4. Antithetic sampling for Monte Carlo differentiable renderingCheng Zhang, Zhao Dong, Michael C. Doggett, Shuang ZhaoSIGGRAPH 2021 · 55 citations
  5. Parameter-space ReSTIR for Differentiable and Inverse RenderingWesley Chang, Venkataram Sivaram, Derek Nowrouzezahrai, Toshiya Hachisuka et al.SIGGRAPH 2023 · 20 citations
Dusk over the sea between two cliffs drawn in fine vertical lines