Neural Poisson: Indicator Functions for Neural Fields
This addresses the problem of accurate 3D surface reconstruction from real scan data for applications in computer vision and graphics, representing a new paradigm rather than an incremental improvement.
The paper tackles 3D shape reconstruction by introducing a Poisson-inspired indicator function representation for neural fields instead of signed distance fields, which enables effective use of empty space constraints from range sensing. The approach achieves state-of-the-art reconstruction performance with a 9.5% improvement in Chamfer distance over existing methods.
Implicit neural field generating signed distance field representations (SDFs) of 3D shapes have shown remarkable progress in 3D shape reconstruction and generation. We introduce a new paradigm for neural field representations of 3D scenes; rather than characterizing surfaces as SDFs, we propose a Poisson-inspired characterization for surfaces as indicator functions optimized by neural fields. Crucially, for reconstruction of real scan data, the indicator function representation enables simple and effective constraints based on common range sensing inputs, which indicate empty space based on line of sight. Such empty space information is intrinsic to the scanning process, and incorporating this knowledge enables more accurate surface reconstruction. We show that our approach demonstrates state-of-the-art reconstruction performance on both synthetic and real scanned 3D scene data, with 9.5% improvement in Chamfer distance over state of the art.