A Deep Visual Correspondence Embedding Model for Stereo Matching Costs
This paper presents a data-driven matching cost for stereo matching. A novel deep visual correspondence embedding model is trained via Convolutional Neural Network on a large set of stereo images with ground truth disparities. This deep embedding model leverages appearance data to learn visual similarity relationships between corresponding image patches, and explicitly maps intensity values into an embedding feature space to measure pixel dissimilarities. Experimental results on KITTI and Middlebury data sets demonstrate the effectiveness of our model. First, we prove that the new measure of pixel dissimilarity outperforms traditional matching costs. Furthermore, when integrated with a global stereo framework, our method ranks top 3 among all two-frame algorithms on the KITTI benchmark. Finally, cross-validation results show that our model is able to make correct predictions for unseen data which are outside of its labeled training set.
Code (0)
등록된 구현이 없습니다.
Tasks
Stereo MatchingStereo Matching HandSimilar Papers 제목 키워드 기반
GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo
Matching cost aggregation plays a fundamental role in learning-based multi-view stereo networks. However, directly aggregating adjacent costs can lead to suboptimal results due to local geometric inconsistency. Related m…
3D ReconstructionParallax Attention for Unsupervised Stereo Correspondence Learning
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-ResolutionMatchAttention: Embedding Explicit Matching Constraints into Attention for Efficient Stereo Matching
Standard attention mechanisms are not well suited to stereo matching. Global attention scales quadratically and provides no explicit matching constraint, while local attention is efficient but loses long-range correspond…
Zero-shot GeneralizationCogStereo: Neural Stereo Matching with Implicit Spatial Cognition Embedding
Deep stereo matching has advanced significantly on benchmark datasets through fine-tuning but falls short of the zero-shot generalization seen in foundation models in other vision tasks. We introduce CogStereo, a novel f…
Zero-shot GeneralizationDomain GeneralizationDisparity EstimationScene UnderstandingMulti-Spectral Visual Odometry without Explicit Stereo Matching
Multi-spectral sensors consisting of a standard (visible-light) camera and a long-wave infrared camera can simultaneously provide both visible and thermal images. Since thermal images are independent from environmental i…
3D ReconstructionStereo MatchingStereo Matching HandVisual Odometry