Inverse Rendering for High-Genus Surface Meshes from Multi-View Images
Preprint
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.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Hierarchical GraphCut Phase Unwrapping Based on Invariance of Diffeomorphisms FrameworkIEEE Open Journal of Signal Processing, 2025
- A Theory of Topological Derivatives for Inverse Rendering of Geometry2023
- Continuous remeshing for inverse renderingComputer Animation and Virtual Worlds, 2022
- Efficient Geometry-aware 3D Generative Adversarial Networks2022
- Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items2022
- Unified Shape and SVBRDF Recovery using Differentiable Monte Carlo RenderingComputer Graphics Forum, 2021
- Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple ImagesInternational Journal of Computer Vision, 2020
- PointFlow: 3D Point Cloud Generation With Continuous Normalizing Flows2019
- Pix2Vox: Context-Aware 3D Reconstruction From Single and Multi-View Images2019
- 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks2018