Co-Teaching: An Ark to Unsupervised Stereo Matching
- URL: http://arxiv.org/abs/2107.08186v1
- Date: Sat, 17 Jul 2021 05:33:39 GMT
- Title: Co-Teaching: An Ark to Unsupervised Stereo Matching
- Authors: Hengli Wang, Rui Fan, Ming Liu
- Abstract summary: CoT-Stereo is a novel unsupervised stereo matching approach.
Experiments on the KITTI Stereo benchmarks demonstrate the superior performance of CoT-Stereo.
- Score: 14.801038005597855
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Stereo matching is a key component of autonomous driving perception. Recent
unsupervised stereo matching approaches have received adequate attention due to
their advantage of not requiring disparity ground truth. These approaches,
however, perform poorly near occlusions. To overcome this drawback, in this
paper, we propose CoT-Stereo, a novel unsupervised stereo matching approach.
Specifically, we adopt a co-teaching framework where two networks interactively
teach each other about the occlusions in an unsupervised fashion, which greatly
improves the robustness of unsupervised stereo matching. Extensive experiments
on the KITTI Stereo benchmarks demonstrate the superior performance of
CoT-Stereo over all other state-of-the-art unsupervised stereo matching
approaches in terms of both accuracy and speed. Our project webpage is
https://sites.google.com/view/cot-stereo.
Related papers
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching [110.22344879336043]
We introduce Stereo Risk, a new deep-learning approach to solve the classical stereo-matching problem in computer vision.
We demonstrate that Stereo Risk enhances stereo-matching performance for deep networks, particularly for disparities with multi-modal probability distributions.
A comprehensive analysis demonstrates our method's theoretical soundness and superior performance over the state-of-the-art methods across various benchmark datasets.
arXiv Detail & Related papers (2024-07-03T14:30:47Z) - Single-View View Synthesis with Self-Rectified Pseudo-Stereo [49.946151180828465]
We leverage the reliable and explicit stereo prior to generate a pseudo-stereo viewpoint.
We propose a self-rectified stereo synthesis to amend erroneous regions in an identify-rectify manner.
Our method outperforms state-of-the-art single-view view synthesis methods and stereo synthesis methods.
arXiv Detail & Related papers (2023-04-19T09:36:13Z) - A novel stereo matching pipeline with robustness and unfixed disparity
search range [5.326626090397465]
Most stereo matching methods have poor generalization performance and require a fixed disparity search range.
We present a new stereo matching pipeline that first computes semi-dense disparity maps based on binocular disparity, and then completes the rest depending on monocular cues.
arXiv Detail & Related papers (2022-04-11T04:53:25Z) - Revisiting Domain Generalized Stereo Matching Networks from a Feature
Consistency Perspective [65.37571681370096]
We propose a simple pixel-wise contrastive learning across the viewpoints.
A stereo selective whitening loss is introduced to better preserve the stereo feature consistency across domains.
Our method achieves superior performance over several state-of-the-art networks.
arXiv Detail & Related papers (2022-03-21T11:21:41Z) - AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach [50.855679274530615]
We present a novel domain-adaptive approach called AdaStereo to align multi-level representations for deep stereo matching networks.
Our models achieve state-of-the-art cross-domain performance on multiple benchmarks, including KITTI, Middlebury, ETH3D and DrivingStereo.
Our method is robust to various domain adaptation settings, and can be easily integrated into quick adaptation application scenarios and real-world deployments.
arXiv Detail & Related papers (2021-12-09T15:10:47Z) - Level Set Binocular Stereo with Occlusions [7.868449549351486]
Localizing stereo boundaries and predicting nearby disparities are difficult because stereo boundaries induce occluded regions where matching cues are absent.
This paper introduces an energy and level-set that improves boundaries by encoding occlusion geometry.
It can be implemented using messages that pass predominantly between parents and children in an undecimated hierarchy of image patches.
arXiv Detail & Related papers (2021-09-08T07:22:25Z) - H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging
Epipolar Geometry [4.968452390132676]
We introduce the H-Net, a deep-learning framework for unsupervised stereo depth estimation.
For the first time, a Siamese autoencoder architecture is used for depth estimation.
Our method outperforms the state-ofthe-art unsupervised stereo depth estimation methods.
arXiv Detail & Related papers (2021-04-22T19:16:35Z) - Parallax Attention for Unsupervised Stereo Correspondence Learning [46.035892564279564]
Stereo image pairs encode 3D scene cues into stereo correspondences between the left and right images.
Recent CNN based methods commonly use cost volume techniques to capture stereo correspondence over large disparities.
We propose a generic parallax-attention mechanism (PAM) to capture stereo correspondence regardless of disparity variations.
arXiv Detail & Related papers (2020-09-16T01:30:13Z) - Reversing the cycle: self-supervised deep stereo through enhanced
monocular distillation [51.714092199995044]
In many fields, self-supervised learning solutions are rapidly evolving and filling the gap with supervised approaches.
We propose a novel self-supervised paradigm reversing the link between the two.
In order to train deep stereo networks, we distill knowledge through a monocular completion network.
arXiv Detail & Related papers (2020-08-17T07:40:22Z) - AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching [50.06646151004375]
A novel domain-adaptive pipeline called AdaStereo aims to align multi-level representations for deep stereo matching networks.
Our AdaStereo models achieve state-of-the-art cross-domain performance on multiple stereo benchmarks, including KITTI, Middlebury, ETH3D, and DrivingStereo.
arXiv Detail & Related papers (2020-04-09T16:15:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.