3D Compression Using Neural Fields
This work addresses 3D data compression for applications in computer graphics and vision, presenting an incremental improvement by adapting neural fields to this domain.
The paper tackles 3D data compression by proposing a neural field-based algorithm with versions for watertight shapes using SDFs and arbitrary shapes using UDFs, achieving effective compression for point clouds and meshes while enabling straightforward extension to compress geometry and attributes like color.
Neural Fields (NFs) have gained momentum as a tool for compressing various data modalities - e.g. images and videos. This work leverages previous advances and proposes a novel NF-based compression algorithm for 3D data. We derive two versions of our approach - one tailored to watertight shapes based on Signed Distance Fields (SDFs) and, more generally, one for arbitrary non-watertight shapes using Unsigned Distance Fields (UDFs). We demonstrate that our method excels at geometry compression on 3D point clouds as well as meshes. Moreover, we show that, due to the NF formulation, it is straightforward to extend our compression algorithm to compress both geometry and attribute (e.g. color) of 3D data.