DiffTetVR: Differentiable Tetrahedral Volume Rendering

TL;DR

DiffTetVR introduces a novel differentiable volume rendering method for tetrahedral meshes, allowing optimization of mesh geometry and subdivision without multigrid techniques, facilitating coarse-to-fine rendering improvements.

Contribution

It presents the first efficient differentiable rendering approach for tetrahedral meshes that enables local subdivision and vertex optimization without relying on multigrid methods.

Findings

Enables vertex position optimization in tetrahedral meshes.

Supports local mesh subdivision for coarse-to-fine rendering.

Provides an efficient implementation with derivative calculations and regularization.

Abstract

Differentiable rendering is a technique that aims to invert the rendering process to enable optimizing rendering parameters from a set of images. In this article, we present a differentiable volume rendering solution called DiffTetVR for tetrahedral meshes. Unlike previous works based on regular grids, this enables the optimization of vertex positions and the local subdivision of the mesh without relying on multigrid methods. We present an efficient implementation of the forward rendering process, deduce the derivatives for the backwards pass and regularization terms for avoiding degenerate tetrahedra, and finally show how the tetrahedral mesh can be subdivided locally to enable a coarse-to-fine optimization process. The source code is made publicly available on GitHub at https://github.com/chrismile/DiffTetVR.