NeuManifold: Neural Watertight Manifold Reconstruction
with Efficient and High-Quality Rendering Support
1UC San Diego, 2Adobe Research, 3ETH Zürich, 4University of Tübingen
*Equal advisory


NeuManifold takes 2D images as input and generates watertight manifold meshes with neural textures, which enables many downstream applications including high-quality novel-view synthesis and soft-body simulation.

Soft-Body Simulation with Real-Time Rendering


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.


Real-Time Interactive Viewer Demos

(Click the object to enter the interactive viewer. Model loading may require long time.)

Real Scene Editing with Soft-Body Simulation


The website template was borrowed from Lior Yariv.