NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support

TL;DR

NeuManifold introduces a hybrid approach combining neural volumetric initialization and differentiable rasterization to produce high-quality, watertight 3D meshes with efficient rendering and broad application compatibility.

Contribution

The paper proposes a novel method that integrates neural volumetric fields with differentiable rasterization for improved 3D mesh reconstruction and rendering efficiency.

Findings

Produces accurate, high-quality watertight meshes

Achieves rendering speeds an order of magnitude faster

Compatible with existing graphics pipelines and applications

Abstract

We present a method for generating high-quality watertight manifold meshes from multi-view input images. Existing volumetric rendering methods are robust in optimization but tend to generate noisy meshes with poor topology. Differentiable rasterization-based methods can generate high-quality meshes but are sensitive to initialization. Our method combines the benefits of both worlds; we take the geometry initialization obtained from neural volumetric fields, and further optimize the geometry as well as a compact neural texture representation with differentiable rasterizers. Through extensive experiments, we demonstrate that our method can generate accurate mesh reconstructions with faithful appearance that are comparable to previous volume rendering methods while being an order of magnitude faster in rendering. We also show that our generated mesh and neural texture reconstruction is compatible with existing graphics pipelines and enables downstream 3D applications such as simulation. Project page: https://sarahweiii.github.io/neumanifold/