NeRFMeshing: Distilling Neural Radiance Fields into Geometrically-Accurate 3D Meshes
This addresses a bottleneck for computer graphics and simulation pipelines by enabling efficient 3D mesh extraction from NeRFs, though it is incremental as it builds on existing NeRF methods.
The paper tackles the challenge of converting Neural Radiance Fields (NeRFs) into accurate 3D meshes, which are essential for real-time rendering and simulations, by proposing a method that distills NeRFs into a Signed Surface Approximation Network, resulting in physically accurate meshes that can be rendered in real time.
With the introduction of Neural Radiance Fields (NeRFs), novel view synthesis has recently made a big leap forward. At the core, NeRF proposes that each 3D point can emit radiance, allowing to conduct view synthesis using differentiable volumetric rendering. While neural radiance fields can accurately represent 3D scenes for computing the image rendering, 3D meshes are still the main scene representation supported by most computer graphics and simulation pipelines, enabling tasks such as real time rendering and physics-based simulations. Obtaining 3D meshes from neural radiance fields still remains an open challenge since NeRFs are optimized for view synthesis, not enforcing an accurate underlying geometry on the radiance field. We thus propose a novel compact and flexible architecture that enables easy 3D surface reconstruction from any NeRF-driven approach. Upon having trained the radiance field, we distill the volumetric 3D representation into a Signed Surface Approximation Network, allowing easy extraction of the 3D mesh and appearance. Our final 3D mesh is physically accurate and can be rendered in real time on an array of devices.