相关论文: Adaptive Unimodal Cost Volume Filtering for Deep S…

Volumetric deep learning approach towards stereo matching aggregates a cost volume computed from input left and right images using 3D convolutions. Recent works showed that utilization of extracted image features and a spatially varying…

We present a new loss function for joint disparity and uncertainty estimation in deep stereo matching. Our work is motivated by the need for precise uncertainty estimates and the observation that multi-task learning often leads to improved…

Despite the remarkable progress of deep learning in stereo matching, there exists a gap in accuracy between real-time models and slower state-of-the-art models which are suitable for practical applications. This paper presents an iterative…

Existing stereo matching networks typically rely on either cost-volume construction based on 3D convolutions or deformation methods based on iterative optimization. The former incurs significant computational overhead during cost…

Recently, records on stereo matching benchmarks are constantly broken by end-to-end disparity networks. However, the domain adaptation ability of these deep models is quite limited. Addressing such problem, we present a novel…

Recently, there has been a paradigm shift in stereo matching with learning-based methods achieving the best results on all popular benchmarks. The success of these methods is due to the availability of training data with ground truth;…

Dense stereo matching with deep neural networks is of great interest to the research community. Existing stereo matching networks typically use slow and computationally expensive 3D convolutions to improve the performance, which is not…

In this paper, we present a decomposition model for stereo matching to solve the problem of excessive growth in computational cost (time and memory cost) as the resolution increases. In order to reduce the huge cost of stereo matching at…

Motivated by the need to identify erroneous disparity assignments, various approaches for uncertainty and confidence estimation of dense stereo matching have been presented in recent years. As in many other fields, especially deep learning…

Stereo matching is one of the most popular techniques to estimate dense depth maps by finding the disparity between matching pixels on two, synchronized and rectified images. Alongside with the development of more accurate algorithms, the…

Stereo matching is vital in 3D computer vision, with most algorithms assuming symmetric visual properties between binocular visions. However, the rise of asymmetric multi-camera systems (e.g., tele-wide cameras) challenges this assumption…

Recently, records on stereo matching benchmarks are constantly broken by end-to-end disparity networks. However, the domain adaptation ability of these deep models is quite poor. Addressing such problem, we present a novel domain-adaptive…

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…

Cost aggregation is a key component of stereo matching for high-quality depth estimation. Most methods use multi-scale processing to downsample cost volume for proper context information, but will cause loss of details when upsampling. In…

Deep neural networks have shown excellent performance in stereo matching task. Recently CNN-based methods have shown that stereo matching can be formulated as a supervised learning task. However, less attention is paid on the fusion of…

In this paper, we have proposed a novel method for stereo disparity estimation by combining the existing methods of block based and region based stereo matching. Our method can generate dense disparity maps from disparity measurements of…

In this paper we present ActiveStereoNet, the first deep learning solution for active stereo systems. Due to the lack of ground truth, our method is fully self-supervised, yet it produces precise depth with a subpixel precision of $1/30th$…

We introduce Double Cost Volume Stereo Matching Network(DCVSMNet) which is a novel architecture characterised by by two small upper (group-wise) and lower (norm correlation) cost volumes. Each cost volume is processed separately, and a…

Despite the great success of deep learning in stereo matching, recovering accurate disparity maps is still challenging. Currently, L1 and cross-entropy are the two most widely used losses for stereo network training. Compared with the…

Learning matching costs has been shown to be critical to the success of the state-of-the-art deep stereo matching methods, in which 3D convolutions are applied on a 4D feature volume to learn a 3D cost volume. However, this mechanism has…