Segment-Tree Based Cost Aggregation for Stereo Matching
This paper presents a novel tree-based cost aggregation method for dense stereo matching. Instead of employing the minimum spanning tree (MST) and its variants, a new tree structure, "Segment-Tree", is proposed for non-local matching cost aggregation. Conceptually, the segment-tree is constructed in a three-step process: first, the pixels are grouped into a set of segments with the reference color or intensity image; second, a tree graph is created for each segment; and in the final step, these independent segment graphs are linked to form the segment-tree structure. In practice, this tree can be efficiently built in time nearly linear to the number of the image pixels. Compared to MST where the graph connectivity is determined with local edge weights, our method introduces some 'non-local' decision rules: the pixels in one perceptually consistent segment are more likely to share similar disparities, and therefore their connectivity within the segment should be first enforced in the tree construction process. The matching costs are then aggregated over the tree within two passes. Performance evaluation on 19 Middlebury data sets shows that the proposed method is comparable to previous state-of-the-art aggregation methods in disparity accuracy and processing speed. Furthermore, the tree structure can be refined with the estimated disparities, which leads to consistent scene segmentation and significantly better aggregation results.
Code (0)
등록된 구현이 없습니다.
Tasks
Scene SegmentationStereo MatchingStereo Matching HandSimilar Papers 제목 키워드 기반
Fast Non-local Stereo Matching based on Hierarchical Disparity Prediction
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 emp…
Stereo MatchingStereo Matching HandMTStereo 2.0: improved accuracy of stereo depth estimation withMax-trees
Efficient yet accurate extraction of depth from stereo image pairs is required by systems with low power resources, such as robotics and embedded systems. State-of-the-art stereo matching methods based on convolutional n…
Depth EstimationGPUStereo Depth EstimationStereo MatchingDeep Stereo Matching with Explicit Cost Aggregation Sub-Architecture
Deep neural networks have shown excellent performance for stereo matching. Many efforts focus on the feature extraction and similarity measurement of the matching cost computation step while less attention is paid on cos…
Stereo MatchingStereo Matching HandDo End-to-end Stereo Algorithms Under-utilize Information?
Deep networks for stereo matching typically leverage 2D or 3D convolutional encoder-decoder architectures to aggregate cost and regularize the cost volume for accurate disparity estimation. Due to content-insensitive con…
DecoderDisparity EstimationStereo MatchingSemantic Stereo Matching With Pyramid Cost Volumes
The accuracy of stereo matching has been greatly improved by using deep learning with convolutional neural networks. To further capture the details of disparity maps, in this paper, we propose a novel semantic stereo net…
Semantic SegmentationStereo Matching