Phase surf improves 3d reconstruction of thin and complex shapes
Volume Rendering with Metric--Phase Fields for Thin Structures and Sign-Ambiguous Geometry
Computer Vision and Pattern Recognition
Summary
When creating 3D models from multiple pictures, neat approaches work well for solid, closed objects but struggle with thin or complex shapes like sheets or tubes. The authors show that a new method called PhaseSurf splits the problem into two parts: measuring how close you are to a surface, and guessing inside versus outside with a soft signal. This helps the computer better handle tricky shapes that confuse older methods. Their tests show PhaseSurf makes clearer, more stable 3D models than previous techniques.
What this means in practice
- •For 3d graphics developers: Build more accurate 3D reconstructions from images that include thin or complex shapes without common errors of older methods.
- •For augmented reality developers: Create realistic 3D models of complex objects with thin parts for better integration into AR environments.
Authors
Junkai Deng, Jiayi Kong, Xuhui Chen, Guanli Hou, Fei Hou, Junhui Hou, Wenping Wang, Ying He
Abstract
Neural implicit surface methods that couple volume rendering with signed distance functions (SDFs), such as VolSDF and NeuS, achieve high-quality multi-view reconstruction for watertight objects. However, these approaches rely on a globally consistent inside-outside partition of space. This assumption becomes fragile for thin structures (e.g., sheets, tubes, and thin walls) and can break down for sign-ambiguous geometry (e.g., surfaces with boundary, non-manifold junctions, and closely spaced surface components), often resulting in spurious closures or loss of fine structures. Unsigned distance field (UDF) formulations relax the global sign requirement and better support non-watertight geometry, but are substantially harder to optimize. We propose PhaseSurf, a neural volume rendering framework built on Metric-Phase Fields (MPFs). MPFs decompose geometry into a nonnegative metric field capturing unsigned proximity and a continuous phase field providing a soft sign cue. By coupling the two through residual phase injection, MPFs yield a signed composite implicit function with stable near-surface gradients while retaining UDF-like robustness in sign-ambiguous regions. This design enables direct iso-surface extraction using standard Marching Cubes and avoids the failure modes of both pure SDF- and UDF-based formulations. We further introduce MPF-specific training losses that enforce metric consistency, stabilize phase transitions near the interface, and suppress spurious geometry in free space. Experiments on multi-view datasets with thin structures and sign-ambiguous geometry show that PhaseSurf produces more stable reconstructions and higher-quality geometry than UDF-based methods and recent 3DGS pipelines, while avoiding artifacts typical of SDF-based approaches.