Adaptive Surface Normal Constraint for Depth Estimation

TL;DR

This paper introduces an Adaptive Surface Normal constraint for single image depth estimation, improving geometric consistency, robustness, and accuracy by adaptively leveraging local geometry information.

Contribution

The novel ASN constraint adaptively determines reliable local geometry to enhance depth estimation with improved geometric consistency and robustness.

Findings

Outperforms state-of-the-art methods in accuracy.

Demonstrates robustness to local shape variations and noise.

Offers superior efficiency in depth reconstruction.

Abstract

We present a novel method for single image depth estimation using surface normal constraints. Existing depth estimation methods either suffer from the lack of geometric constraints, or are limited to the difficulty of reliably capturing geometric context, which leads to a bottleneck of depth estimation quality. We therefore introduce a simple yet effective method, named Adaptive Surface Normal (ASN) constraint, to effectively correlate the depth estimation with geometric consistency. Our key idea is to adaptively determine the reliable local geometry from a set of randomly sampled candidates to derive surface normal constraint, for which we measure the consistency of the geometric contextual features. As a result, our method can faithfully reconstruct the 3D geometry and is robust to local shape variations, such as boundaries, sharp corners and noises. We conduct extensive evaluations and comparisons using public datasets. The experimental results demonstrate our method outperforms the state-of-the-art methods and has superior efficiency and robustness.