Related papers: Integrating Disparity Confidence Estimation into R…

Leveraging the disparity information from both left and right views is crucial for stereo disparity estimation. Left-right consistency check is an effective way to enhance the disparity estimation by referring to the information from the…

This paper presents HITNet, a novel neural network architecture for real-time stereo matching. Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not…

Stereo matching is one of the widely used techniques for inferring depth from stereo images owing to its robustness and speed. It has become one of the major topics of research since it finds its applications in autonomous driving, robotic…

Depth estimation from a stereo image pair has become one of the most explored applications in computer vision, with most of the previous methods relying on fully supervised learning settings. However, due to the difficulty in acquiring…

The field of self-supervised monocular depth estimation has seen huge advancements in recent years. Most methods assume stereo data is available during training but usually under-utilize it and only treat it as a reference signal. We…

Both uncertainty-assisted and iteration-based methods have achieved great success in stereo matching. However, existing uncertainty estimation methods take a single image and the corresponding disparity as input, which imposes higher…

In this work, we concentrate on exciting the intrinsic local consistency of stereo matching through the incorporation of superpixel soft constraints, with the objective of mitigating inaccuracies at the boundaries of predicted disparity…

Monocular depth inference has gained tremendous attention from researchers in recent years and remains as a promising replacement for expensive time-of-flight sensors, but issues with scale acquisition and implementation overhead still…

We revisit the problem of visual depth estimation in the context of autonomous vehicles. Despite the progress on monocular depth estimation in recent years, we show that the gap between monocular and stereo depth accuracy remains large$-$a…

Both optical flow and stereo disparities are image matches and can therefore benefit from joint training. Depth and 3D motion provide geometric rather than photometric information and can further improve optical flow. Accordingly, we design…

Depth estimation is a crucial step for image-guided intervention in robotic surgery and laparoscopic imaging system. Since per-pixel depth ground truth is difficult to acquire for laparoscopic image data, it is rarely possible to apply…

The success of existing deep-learning based multi-view stereo (MVS) approaches greatly depends on the availability of large-scale supervision in the form of dense depth maps. Such supervision, while not always possible, tends to hinder the…

Deep learning (DL) methods are widely investigated for stereo image matching tasks due to their reported high accuracies. However, their transferability/generalization capabilities are limited by the instances seen in the training data.…

Despite stereo matching accuracy has greatly improved by deep learning in the last few years, recovering sharp boundaries and high-resolution outputs efficiently remains challenging. In this paper, we propose Stereo Mixture Density Networks…

Stereo matching is the key step in estimating depth from two or more images. Recently, some tree-based non-local stereo matching methods have been proposed, which achieved state-of-the-art performance. The algorithms employed some tree…

Unsupervised depth learning takes the appearance difference between a target view and a view synthesized from its adjacent frame as supervisory signal. Since the supervisory signal only comes from images themselves, the resolution of…

Recent supervised multi-view depth estimation networks have achieved promising results. Similar to all supervised approaches, these networks require ground-truth data during training. However, collecting a large amount of multi-view depth…

Monocular depth estimation has been extensively explored based on deep learning, yet its accuracy and generalization ability still lag far behind the stereo-based methods. To tackle this, a few recent studies have proposed to supervise the…

Although deep learning-based methods have dominated stereo matching leaderboards by yielding unprecedented disparity accuracy, their inference time is typically slow, on the order of seconds for a pair of 540p images. The main reason is…

Supervised learning methods to infer (hypothesize) depth of a scene from a single image require costly per-pixel ground-truth. We follow a geometric approach that exploits abundant stereo imagery to learn a model to hypothesize scene…