Inverse Rendering for High-Genus Surface Meshes from Multi-View Images

TL;DR

This paper introduces a topology-aware inverse rendering method that reconstructs high-genus surface meshes from multi-view images, overcoming gradient issues and preserving topological features, outperforming existing approaches especially on complex surfaces.

Contribution

The paper proposes an adaptive V-cycle remeshing scheme combined with a re-parametrized Adam optimizer to improve inverse rendering of high-genus meshes, ensuring topological consistency and detailed surface reconstruction.

Findings

Outperforms state-of-the-art in Chamfer Distance and Volume IoU.

Effectively preserves topological features of high-genus surfaces.

Enhances surface detail for low-genus surfaces.

Abstract

We present a topology-informed inverse rendering approach for reconstructing high-genus surface meshes from multi-view images. Compared to 3D representations like voxels and point clouds, mesh-based representations are preferred as they enable the application of differential geometry theory and are optimized for modern graphics pipelines. However, existing inverse rendering methods often fail catastrophically on high-genus surfaces, leading to the loss of key topological features, and tend to oversmooth low-genus surfaces, resulting in the loss of surface details. This failure stems from their overreliance on Adam-based optimizers, which can lead to vanishing and exploding gradients. To overcome these challenges, we introduce an adaptive V-cycle remeshing scheme in conjunction with a re-parametrized Adam optimizer to enhance topological and geometric awareness. By periodically coarsening and refining the deforming mesh, our method informs mesh vertices of their current topology and geometry before optimization, mitigating gradient issues while preserving essential topological features. Additionally, we enforce topological consistency by constructing topological primitives with genus numbers that match those of ground truth using Gauss-Bonnet theorem. Experimental results demonstrate that our inverse rendering approach outperforms the current state-of-the-art method, achieving significant improvements in Chamfer Distance and Volume IoU, particularly for high-genus surfaces, while also enhancing surface details for low-genus surfaces.