DiffTrans: Differentiable Geometry-Materials Decomposition for Reconstructing Transparent Objects

TL;DR

DiffTrans introduces a differentiable rendering framework that accurately reconstructs transparent objects with complex topology and textures from multi-view images, overcoming limitations of prior methods.

Contribution

It proposes a novel end-to-end differentiable framework combining FlexiCubes and a recursive ray tracer for efficient geometry and material decomposition of transparent objects.

Findings

Outperforms existing methods on multiple benchmarks.

Achieves high-quality reconstruction in complex scenes.

Reduces computational cost with CUDA implementation.

Abstract

Reconstructing transparent objects from a set of multi-view images is a challenging task due to the complicated nature and indeterminate behavior of light propagation. Typical methods are primarily tailored to specific scenarios, such as objects following a uniform topology, exhibiting ideal transparency and surface specular reflections, or with only surface materials, which substantially constrains their practical applicability in real-world settings. In this work, we propose a differentiable rendering framework for transparent objects, dubbed DiffTrans, which allows for efficient decomposition and reconstruction of the geometry and materials of transparent objects, thereby reconstructing transparent objects accurately in intricate scenes with diverse topology and complex texture. Specifically, we first utilize FlexiCubes with dilation and smoothness regularization as the iso-surface representation to reconstruct an initial geometry efficiently from the multi-view object silhouette. Meanwhile, we employ the environment light radiance field to recover the environment of the scene. Then we devise a recursive differentiable ray tracer to further optimize the geometry, index of refraction and absorption rate simultaneously in a unified and end-to-end manner, leading to high-quality reconstruction of transparent objects in intricate scenes. A prominent advantage of the designed ray tracer is that it can be implemented in CUDA, enabling a significantly reduced computational cost. Extensive experiments on multiple benchmarks demonstrate the superior reconstruction performance of our DiffTrans compared with other methods, especially in intricate scenes involving transparent objects with diverse topology and complex texture. The code is available at https://github.com/lcp29/DiffTrans.