The core message of this article is that the authors propose a self-supervised monocular depth estimation framework that leverages specular reflection priors in water scenes to reformulate the ill-posed depth estimation task as an interpretable multi-view synthesis problem.
This work presents Depth Anything, a highly practical solution for robust monocular depth estimation. By scaling up the dataset with large-scale unlabeled data and employing effective training strategies, the model exhibits impressive generalization ability across extensive unseen scenes.
Leveraging language priors in a variational framework to improve metric-scale monocular depth estimation.
A learnable module called Adaptive Discrete Disparity Volume (ADDV) is proposed to dynamically generate adaptive depth bins and estimate probability distributions for self-supervised monocular depth estimation, outperforming handcrafted discretization strategies.
A method to improve the localization of depth edges in sparsely-supervised monocular depth estimation models, while preserving per-pixel depth accuracy.
Explicitly leveraging edge information is critical for producing high-quality monocular depth maps with clear edges and details.