# Plateau-reduced Differentiable Path Tracing

arXiv: https://arxiv.org/abs/2211.17263 · HTML: https://mlsanity.com/paper/2211.17263/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 55 references that are in the map.
- First posted on arXiv 30 Nov 2022.

## Builds on (most cited first, 29 of 29)

- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [Modular Primitives for High-Performance Differentiable Rendering](https://mlsanity.com/paper/2011.03277/) (2020)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering](https://mlsanity.com/paper/2106.02634/) (2021)
- [How to Escape Saddle Points Efficiently](https://mlsanity.com/paper/1703.00887/) (2017)
- [Differentiable Surface Splatting for Point-based Geometry Processing](https://mlsanity.com/paper/1906.04173/) (2019)
- [Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer](https://mlsanity.com/paper/1908.01210/) (2019)
- [DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracing](https://mlsanity.com/paper/1911.13225/) (2019)
- [Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency](https://mlsanity.com/paper/1704.06254/) (2017)
- [SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization](https://mlsanity.com/paper/1912.07109/) (2019)
- [Differentiable Rendering: A Survey](https://mlsanity.com/paper/2006.12057/) (2020)
- [Gradient Estimation Using Stochastic Computation Graphs](https://mlsanity.com/paper/1506.05254/) (2015)
- [Im2Vec: Synthesizing Vector Graphics without Vector Supervision](https://mlsanity.com/paper/2102.02798/) (2021)
- [Unsupervised Learning of Shape and Pose with Differentiable Point Clouds](https://mlsanity.com/paper/1810.09381/) (2018)
- [Do Differentiable Simulators Give Better Policy Gradients?](https://mlsanity.com/paper/2202.00817/) (2022)
- [Gradients are Not All You Need](https://mlsanity.com/paper/2111.05803/) (2021)
- [Deep Shading: Convolutional Neural Networks for Screen-Space Shading](https://mlsanity.com/paper/1603.06078/) (2016)
- [A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation](https://mlsanity.com/paper/1602.03725/) (2016)
- [Eikonal Fields for Refractive Novel-View Synthesis](https://mlsanity.com/paper/2202.00948/) (2022)
- [Differentiable Surface Rendering via Non-Differentiable Sampling](https://mlsanity.com/paper/2108.04886/) (2021)
- [Pix2Vex: Image-to-Geometry Reconstruction using a Smooth Differentiable Renderer](https://mlsanity.com/paper/1903.11149/) (2019)
- [Node Graph Optimization Using Differentiable Proxies](https://mlsanity.com/paper/2207.07684/) (2022)
- [GenDR: A Generalized Differentiable Renderer](https://mlsanity.com/paper/2204.13845/) (2022)
- [Efficient and Differentiable Shadow Computation for Inverse Problems](https://mlsanity.com/paper/2104.00359/) (2021)
- [Metappearance: Meta-Learning for Visual Appearance Reproduction](https://mlsanity.com/paper/2204.08993/) (2022)
- [Learning to Learn and Sample BRDFs](https://mlsanity.com/paper/2210.03510/) (2022)
- [Differentiable Rendering with Perturbed Optimizers](https://mlsanity.com/paper/2110.09107/) (2021)
- [Deep-learning the Latent Space of Light Transport](https://mlsanity.com/paper/1811.04756/) (2018)
- [Learning Neural Light Transport](https://mlsanity.com/paper/2006.03427/) (2020)

## Built on by (most cited first, 10 of 10)

- [IllumiNeRF: 3D Relighting Without Inverse Rendering](https://mlsanity.com/paper/2406.06527/) (2024)
- [NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs](https://mlsanity.com/paper/2402.08622/) (2024)
- [Accurate Differential Operators for Hybrid Neural Fields](https://mlsanity.com/paper/2312.05984/) (2023)
- [Differentiable Light Transport with Gaussian Surfels via Adapted Radiosity for Efficient Relighting and Geometry Reconstruction](https://mlsanity.com/paper/2509.18497/) (2025)
- [Many-Worlds Inverse Rendering](https://mlsanity.com/paper/2408.16005/) (2024)
- [Locally Orderless Images for Optimization in Differentiable Rendering](https://mlsanity.com/paper/2503.21931/) (2025)
- [Fast and Accurate Neural Rendering Using Semi-Gradients](https://mlsanity.com/paper/2410.10149/) (2024)
- [Learning Neural Antiderivatives](https://mlsanity.com/paper/2509.17755/) (2025)
- [DiffBMP: Differentiable Rendering with Bitmap Primitives](https://mlsanity.com/paper/2602.22625/) (2026)
- [Feature-Guided Diffusion for Non-Differentiable Inverse Rendering](https://mlsanity.com/paper/2607.17411/) (2026)

## Abstract (arXiv)

Current differentiable renderers provide light transport gradients with respect to arbitrary scene parameters. However, the mere existence of these gradients does not guarantee useful update steps in an optimization. Instead, inverse rendering might not converge due to inherent plateaus, i.e., regions of zero gradient, in the objective function. We propose to alleviate this by convolving the high-dimensional rendering function that maps scene parameters to images with an additional kernel that blurs the parameter space. We describe two Monte Carlo estimators to compute plateau-free gradients efficiently, i.e., with low variance, and show that these translate into net-gains in optimization error and runtime performance. Our approach is a straightforward extension to both black-box and differentiable renderers and enables optimization of problems with intricate light transport, such as caustics or global illumination, that existing differentiable renderers do not converge on.