DMesh++: An Efficient Differentiable Mesh for Complex Shapes

1. University of Maryland, College Park
2. Adobe Research
* This work was done during internship at Adobe Research.

DMesh++ is an efficient differentiable mesh-based method that can effectively handle complex 2D and 3D shapes. For instance, it can be used for reconstructing complex shapes from point clouds and multi-view images, as illustrated in the first figure. The second video demonstrates the optimization process of DMesh++ as it reconstructs diverse 3D shapes from multi-view color and depth images. For each example, some of the corresponding color and depth images are shown on the right side of the video. Note that DMesh++ accurately captures fine details across various shapes.

Abstract

Recent probabilistic methods for 3D triangular meshes capture diverse shapes by differentiable mesh connectivity, but face high computational costs with increased shape details. We introduce a new differentiable mesh processing method in 2D and 3D that addresses this challenge and efficiently handles meshes with intricate structures. Additionally, we present an algorithm that adapts the mesh resolution to local geometry in 2D for efficient representation. We demonstrate the effectiveness of our approach on 2D point cloud and 3D multi-view reconstruction tasks.

2D Point Cloud Reconstruction

Results: Complex Drawings

Left: Real part and imaginary part together / Right: Mesh (Real part) only.

3D Multi-View Reconstruction

In this task, we reconstruct a 3D mesh from multi-view color (or diffuse) and depth images taken from 64 viewpoints by minimizing a rendering loss. Below, we show videos of the 3D mesh as it undergoes reconstruction, side by side with four of the input images, each featuring a black background.

Physics Simulation

We can reconstruct a small scene from multi-view images as shown below, and run physics simulation directly on the reconstructed mesh.

BibTeX

@misc{son2024dmeshefficientdifferentiablemesh,
      title={DMesh++: An Efficient Differentiable Mesh for Complex Shapes}, 
      author={Sanghyun Son and Matheus Gadelha and Yang Zhou and Matthew Fisher and Zexiang Xu and Yi-Ling Qiao and Ming C. Lin and Yi Zhou},
      year={2024},
      eprint={2412.16776},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2412.16776}, 
}