cs.CVNov 12, 2026

Learning the Missing Derivative: Neural Multiple-Scattering Operators for Inverse Volume Rendering

Authors: Sipeng Chen, Shibo Li

Organizations: Department of Computer Science, Florida State University

Abstract

Reconstructing optically thick media from photographs requires modeling multiple scattering and its response to changes in extinction. Frozen-source tomography discards this derivative; differentiable path tracing estimates it through expensive, noisy sampling. We instead predict the multiple-scattering field with a neural operator and differentiate through it during inverse rendering, while computing transmittance and single scattering directly. A further challenge arises during optimization: an operator that predicts the field accurately on held-out media can still produce poor derivatives at the density states visited by the optimizer. We address this by fine-tuning on states generated during inversions driven by the operator, using Monte Carlo scattering-field supervision. On held-out optically thick clouds, our method improves relighting over frozen-source tomography at equal time and outperforms differentiable path tracing given substantially more time. Training on inversion trajectories also improves derivative alignment at visited states and reduces optimization drift.

Figures & tables

Appendix figures & tables20 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Differentiable Inverse Rendering Recovers Intrinsic Properties from Intravascular Optical Coherence Tomography

    Nov 9, 2026Ajay Manicka, Karim Kadry, Sebastian Ruiz-Lopera +7Optical Coherence TomographyInverse Rendering

  2. Differentiable Polarized Path Tracing

    Jul 14, 2026Pramod Rao, Jérémy Riviere, Xilong Zhou +6Inverse RenderingDifferentiable Rendering

  3. Extracting Neural Materials from Multi-view Images

    Jun 25, 2026Kim Youwang, Jon Hasselgren, Peter Kocsis +3Inverse RenderingDifferentiable Rendering