A Simple Approach to Differentiable Rendering of SDFs

TL;DR

This paper introduces a straightforward differentiable rendering algorithm for Signed Distance Fields that simplifies integration into optimization pipelines by balancing bias and variance, achieving competitive results.

Contribution

It proposes a simple, low-variance method for differentiable rendering of SDFs that avoids complex data structures and reparameterization, improving robustness and ease of use.

Findings

Achieves competitive inverse rendering results.

Demonstrates robustness and simplicity of the approach.

Outperforms some existing methods in accuracy.

Abstract

We present a simple algorithm for differentiable rendering of surfaces represented by Signed Distance Fields (SDF), which makes it easy to integrate rendering into gradient-based optimization pipelines. To tackle visibility-related derivatives that make rendering non-differentiable, existing physically based differentiable rendering methods often rely on elaborate guiding data structures or reparameterization with a global impact on variance. In this article, we investigate an alternative that embraces nonzero bias in exchange for low variance and architectural simplicity. Our method expands the lower-dimensional boundary integral into a thin band that is easy to sample when the underlying surface is represented by an SDF. We demonstrate the performance and robustness of our formulation in end-to-end inverse rendering tasks, where it obtains results that are competitive with or superior to existing work.