Related papers: FG-Depth: Flow-Guided Unsupervised Monocular Depth…
Self-supervised monocular depth estimation has emerged as a promising method because it does not require groundtruth depth maps during training. As an alternative for the groundtruth depth map, the photometric loss enables to provide…
A new unsupervised learning method of depth and ego-motion using multiple masks from monocular video is proposed in this paper. The depth estimation network and the ego-motion estimation network are trained according to the constraints of…
Self-supervised monocular depth estimation has been widely studied, owing to its practical importance and recent promising improvements. However, most works suffer from limited supervision of photometric consistency, especially in weak…
We present two versatile methods to generally enhance self-supervised monocular depth estimation (MDE) models. The high generalizability of our methods is achieved by solving the fundamental and ubiquitous problems in photometric loss…
Over the past few years, self-supervised monocular depth estimation that does not depend on ground-truth during the training phase has received widespread attention. Most efforts focus on designing different types of network architectures…
Self-supervised monocular scene flow estimation, aiming to understand both 3D structures and 3D motions from two temporally consecutive monocular images, has received increasing attention for its simple and economical sensor setup. However,…
Self-supervised learning for depth estimation uses geometry in image sequences for supervision and shows promising results. Like many computer vision tasks, depth network performance is determined by the capability to learn accurate spatial…
Depth estimation plays an important role in the robotic perception system. Self-supervised monocular paradigm has gained significant attention since it can free training from the reliance on depth annotations. Despite recent advancements,…
Scene flow represents the motion of points in the 3D space, which is the counterpart of the optical flow that represents the motion of pixels in the 2D image. However, it is difficult to obtain the ground truth of scene flow in the real…
Self-supervised methods play an increasingly important role in monocular depth estimation due to their great potential and low annotation cost. To close the gap with supervised methods, recent works take advantage of extra constraints,…
We present an unsupervised learning framework for simultaneously training single-view depth prediction and optical flow estimation models using unlabeled video sequences. Existing unsupervised methods often exploit brightness constancy and…
Recent techniques in self-supervised monocular depth estimation are approaching the performance of supervised methods, but operate in low resolution only. We show that high resolution is key towards high-fidelity self-supervised monocular…
Obtaining accurate depth measurements out of a single image represents a fascinating solution to 3D sensing. CNNs led to considerable improvements in this field, and recent trends replaced the need for ground-truth labels with…
Monocular depth estimation is a challenging task that predicts the pixel-wise depth from a single 2D image. Current methods typically model this problem as a regression or classification task. We propose DiffusionDepth, a new approach that…
Image-based depth estimation has gained significant attention in recent research on computer vision for autonomous vehicles in intelligent transportation systems. This focus stems from its cost-effectiveness and wide range of potential…
We present a novel unsupervised learning framework for single view depth estimation using monocular videos. It is well known in 3D vision that enlarging the baseline can increase the depth estimation accuracy, and jointly optimizing a set…
We present GLNet, a self-supervised framework for learning depth, optical flow, camera pose and intrinsic parameters from monocular video - addressing the difficulty of acquiring realistic ground-truth for such tasks. We propose three…
Denoising diffusion probabilistic models have transformed image generation with their impressive fidelity and diversity. We show that they also excel in estimating optical flow and monocular depth, surprisingly, without task-specific…
Deep neural networks have recently thrived on single image depth estimation. That being said, current developments on this topic highlight an apparent compromise between accuracy and network size. This work proposes an accurate and…
Multi-frame depth estimation improves over single-frame approaches by also leveraging geometric relationships between images via feature matching, in addition to learning appearance-based features. In this paper we revisit feature matching…