HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity

TL;DR

HiNeuS introduces a unified neural surface reconstruction framework that effectively handles low-texture and reflective ambiguities, achieving high geometric fidelity and photometric consistency in complex scenes.

Contribution

The paper presents HiNeuS, a novel integrated approach combining visibility verification, local surface regularization, and adaptive Eikonal constraints for improved neural surface reconstruction.

Findings

21.4% reduction in Chamfer distance over baselines

2.32 dB PSNR improvement in neural rendering

Effective recovery of specular surfaces and low-texture details

Abstract

Neural surface reconstruction faces persistent challenges in reconciling geometric fidelity with photometric consistency under complex scene conditions. We present HiNeuS, a unified framework that holistically addresses three core limitations in existing approaches: multi-view radiance inconsistency, missing keypoints in textureless regions, and structural degradation from over-enforced Eikonal constraints during joint optimization. To resolve these issues through a unified pipeline, we introduce: 1) Differential visibility verification through SDF-guided ray tracing, resolving reflection ambiguities via continuous occlusion modeling; 2) Planar-conformal regularization via ray-aligned geometry patches that enforce local surface coherence while preserving sharp edges through adaptive appearance weighting; and 3) Physically-grounded Eikonal relaxation that dynamically modulates geometric constraints based on local radiance gradients, enabling detail preservation without sacrificing global regularity. Unlike prior methods that handle these aspects through sequential optimizations or isolated modules, our approach achieves cohesive integration where appearance-geometry constraints evolve synergistically throughout training. Comprehensive evaluations across synthetic and real-world datasets demonstrate state-of-the-art performance, including a 21.4% reduction in Chamfer distance over reflection-aware baselines and 2.32 dB PSNR improvement against neural rendering counterparts. Qualitative analyses reveal superior capability in recovering specular instruments, urban layouts with centimeter-scale infrastructure, and low-textured surfaces without local patch collapse. The method's generalizability is further validated through successful application to inverse rendering tasks, including material decomposition and view-consistent relighting.