DMesh++: An Efficient Differentiable Mesh for Complex Shapes
This work addresses efficiency bottlenecks in 3D shape reconstruction for computer vision and graphics applications, representing a strong incremental improvement over existing methods.
The paper tackles the high computational cost of probabilistic methods for 3D triangular meshes by introducing a new differentiable mesh processing method that reduces time complexity from O(N) to O(log N) and significantly lowers memory usage, enabling efficient handling of intricate structures.
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 that addresses this challenge and efficiently handles meshes with intricate structures. Our method reduces time complexity from O(N) to O(log N) and requires significantly less memory than previous approaches. Building on this innovation, we present a reconstruction algorithm capable of generating complex 2D and 3D shapes from point clouds or multi-view images. Visit our project page (https://sonsang.github.io/dmesh2-project) for source code and supplementary material.