Adaptive Surface Normal Constraint for Depth Estimation

03/29/2021
by   Xiaoxiao Long, et al.
10

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.

READ FULL TEXT

page 1

page 3

page 6

page 7

research
10/07/2022

IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty

Single image surface normal estimation and depth estimation are closely ...
research
03/04/2021

Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos

A key challenge of learning the geometry of dressed humans lies in the l...
research
04/02/2020

Occlusion-Aware Depth Estimation with Adaptive Normal Constraints

We present a new learning-based method for multi-frame depth estimation ...
research
11/10/2017

Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency

Learning to reconstruct depths in a single image by watching unlabeled v...
research
03/21/2018

Robust Depth Estimation from Auto Bracketed Images

As demand for advanced photographic applications on hand-held devices gr...
research
06/07/2020

SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation

We propose a novel method for combining synthetic and real images when t...
research
04/24/2023

D2NT: A High-Performing Depth-to-Normal Translator

Surface normal holds significant importance in visual environmental perc...

Please sign up or login with your details

Forgot password? Click here to reset