paper-with-me

Papers

Left-Right Comparative Recurrent Model for Stereo Matching

2018-04-03 · CVPR 2018 6 · Zequn Jie, Pengfei Wang, Yonggen Ling, Bo Zhao, Yunchao Wei, Jiashi Feng, Wei Liu

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 opposite view. However, the conventional left-right consistency check is an isolated post-processing step and heavily hand-crafted. This paper proposes a novel left-right comparative recurrent model to perform left-right consistency checking jointly with disparity estimation. At each recurrent step, the model produces disparity results for both views, and then performs online left-right comparison to identify the mismatched regions which may probably contain erroneously labeled pixels. A soft attention mechanism is introduced, which employs the learned error maps for better guiding the model to selectively focus on refining the unreliable regions at the next recurrent step. In this way, the generated disparity maps are progressively improved by the proposed recurrent model. Extensive evaluations on KITTI 2015, Scene Flow and Middlebury benchmarks validate the effectiveness of our model, demonstrating that state-of-the-art stereo disparity estimation results can be achieved by this new model.

📄 PDF Abstract BibTeX arXiv:1804.00796

Code (0)

등록된 구현이 없습니다.

Tasks

Disparity EstimationmodelStereo Disparity EstimationStereo MatchingStereo Matching Hand

Similar Papers 제목 키워드 기반

Left-right Discrepancy for Adversarial Attack on Stereo Networks

2024-01-14 · Pengfei Wang, Xiaofei Hui, Beijia Lu, Nimrod Lilith 외

Stereo matching neural networks often involve a Siamese structure to extract intermediate features from left and right images. The similarity between these intermediate left-right features significantly impacts the accur…

Adversarial AttackDisparity EstimationStereo Matching

DMS:Diffusion-Based Multi-Baseline Stereo Generation for Improving Self-Supervised Depth Estimation

2025-08-18 · Zihua Liu, Yizhou Li, Songyan Zhang, Masatoshi Okutomi arxiv

While supervised stereo matching and monocular depth estimation have advanced significantly with learning-based algorithms, self-supervised methods using stereo images as supervision signals have received relatively less…

Monocular Depth Estimation

Parallax Attention for Unsupervised Stereo Correspondence Learning

2020-09-16 · Longguang Wang, Yulan Guo, Yingqian Wang, Zhengfa Liang 외

Stereo image pairs encode 3D scene cues into stereo correspondences between the left and right images. To exploit 3D cues within stereo images, recent CNN based methods commonly use cost volume techniques to capture ster…

Image Super-ResolutionStereo Image Super-ResolutionStereo MatchingSuper-Resolution

Computing the Stereo Matching Cost with a Convolutional Neural Network

2014-09-15 · CVPR 2015 6 · Jure Žbontar, Yann Lecun

We present a method for extracting depth information from a rectified image pair. We train a convolutional neural network to predict how well two image patches match and use it to compute the stereo matching cost. The co…

Stereo MatchingStereo Matching Hand

Stereo Computation for a Single Mixture Image

2018-08-27 · ECCV 2018 9 · Yiran Zhong, Yuchao Dai, Hongdong Li

This paper proposes an original problem of \emph{stereo computation from a single mixture image}-- a challenging problem that had not been researched before. The goal is to separate (\ie, unmix) a single mixture image in…

Stereo MatchingStereo Matching Handvalid