Adaptive Surface Normal Constraint for Depth Estimation
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.
Code (1)
Tasks
3D geometryDepth EstimationSimilar Papers 제목 키워드 기반
Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Images
We introduce a novel approach to learn geometries such as depth and surface normal from images while incorporating geometric context. The difficulty of reliably capturing geometric context in existing methods impedes the…
3D geometryDepth EstimationCORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision
The ill-posed nature of monocular 3D geometry (depth map and surface normals) estimation makes it rely mostly on data-driven approaches such as Deep Neural Networks (DNN). However, data acquisition of surface normals…
3D geometryDepth EstimationMulti-Task LearningSurface Normal Estimation+1D2NT: A High-Performing Depth-to-Normal Translator
Surface normal holds significant importance in visual environmental perception, serving as a source of rich geometric information. However, the state-of-the-art (SoTA) surface normal estimators (SNEs) generally suffer fr…
Surface Normal EstimationVocal Bursts Intensity PredictionDeep Surface Normal Estimation with Hierarchical RGB-D Fusion
The growing availability of commodity RGB-D cameras has boosted the applications in the field of scene understanding. However, as a fundamental scene understanding task, surface normal estimation from RGB-D data lacks th…
Scene UnderstandingSurface Normal EstimationNDDepth: Normal-Distance Assisted Monocular Depth Estimation and Completion
Over the past few years, monocular depth estimation and completion have been paid more and more attention from the computer vision community because of their widespread applications. In this paper, we introduce novel phy…
Depth EstimationMonocular Depth Estimation