Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functions

TL;DR

This paper introduces a novel volume rendering approach that explicitly senses surface patches to improve the inference of signed distance functions, leading to more accurate 3D geometry reconstruction from multi-view images.

Contribution

It proposes a method to explicitly sense surface patches in volume rendering, enhancing surface constraints for better signed distance function inference.

Findings

Outperforms recent methods on scene benchmarks.

Provides more detailed and accurate surface reconstructions.

Demonstrates effectiveness through numerical and visual comparisons.

Abstract

It is vital to recover 3D geometry from multi-view RGB images in many 3D computer vision tasks. The latest methods infer the geometry represented as a signed distance field by minimizing the rendering error on the field through volume rendering. However, it is still challenging to explicitly impose constraints on surfaces for inferring more geometry details due to the limited ability of sensing surfaces in volume rendering. To resolve this problem, we introduce a method to infer signed distance functions (SDFs) with a better sense of surfaces through volume rendering. Using the gradients and signed distances, we establish a small surface patch centered at the estimated intersection along a ray by pulling points randomly sampled nearby. Hence, we are able to explicitly impose surface constraints on the sensed surface patch, such as multi-view photo consistency and supervision from depth or normal priors, through volume rendering. We evaluate our method by numerical and visual comparisons on scene benchmarks. Our superiority over the latest methods justifies our effectiveness.