The Farther the Better: Balanced Stereo Matching via Depth-Based Sampling and Adaptive Feature Refinement

Zhang, Hong; Ye, Xinchen; Chen, Shenglun; Wang, Zhihui; Li, Haojie; Ouyang, Wanli

doi:10.1109/tcsvt.2021.3133353

Cited by 6 publications

(2 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way, the computational efficiency is sacrificed in exchange for reducing memory cost. When the coarse-to-fine methods [3], [4], [43]- [45] are adopted, the cost volume at the coarsest stage is constructed by uniformly sampling depth planes [46] of all depth hypotheses. Then the depth map is refined iteratively by building a more compact cost volume according to the estimated depth in previous stage as an initialization.…”

Section: A Learning-based Mvsmentioning

confidence: 99%

RobustMVS: Single Domain Generalized Deep Multi-View Stereo

Xu,

Chen,

Sun

et al. 2024

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Despite the impressive performance of Multi-view Stereo (MVS) approaches given plenty of training samples, the performance degradation when generalizing to unseen domains has not been clearly explored yet. In this work, we focus on the domain generalization problem in MVS. To evaluate the generalization results, we build a novel MVS domain generalization benchmark including synthetic and real-world datasets. In contrast to conventional domain generalization benchmarks, we consider a more realistic but challenging scenario, where only one source domain is available for training. The MVS problem can be analogized back to the feature matching task, and maintaining robust feature consistency among views is an important factor for improving generalization performance. To address the domain generalization problem in MVS, we propose a novel MVS framework, namely RobustMVS 1 . A Depth-Clustering-guided Whitening (DCW) loss is further introduced to preserve the feature consistency among different views, which decorrelates multi-view features from viewpoint-specific style information based on geometric priors from depth maps. The experimental results further show that our method achieves superior performance on the domain generalization benchmark 2 .

show abstract

Section: A Learning-based Mvsmentioning

confidence: 99%

RobustMVS: Single Domain Generalized Deep Multi-View Stereo

Xu,

Chen,

Sun

et al. 2024

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…Standard disparity estimation methods, with dual-intensity stereo cameras, employ neural networks to search the pixelto-pixel correspondence between two views of the epipolar line, relying on the assumption that the stereo image pair shares the same modalities and ideal exposures [33]- [38]. To reduce the dependence of the disparity estimation performance on high-quality imaging conditions, recent works replace one intensity camera with an event camera to build the stereo event and intensity camera setup and explore the cross-modal stereo matching task [39]- [42].…”

Section: Disparity Estimationmentioning

confidence: 99%

Learning Event-Based Motion Deblurring

Jiang

Zhang

Zou³

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

149

View full text Add to dashboard Cite

Due to the extremely low latency, events have been recently exploited to supplement lost information for motion deblurring. Existing approaches largely rely on the perfect pixelwise alignment between intensity images and events, which is not always fulfilled in the real world. To tackle this problem, we propose a novel coarse-to-fine framework, named NETwork of Event-based motion Deblurring with STereo event and intensity cameras (St-EDNet), to recover high-quality images directly from the misaligned inputs, consisting of a single blurry image and the concurrent event streams. Specifically, the coarse spatial alignment of the blurry image and the event streams is first implemented with a cross-modal stereo matching module without the need for ground-truth depths. Then, a dual-feature embedding architecture is proposed to gradually build the fine bidirectional association of the coarsely aligned data and reconstruct the sequence of the latent sharp images. Furthermore, we build a new dataset with STereo Event and Intensity Cameras (StEIC), containing real-world events, intensity images, and dense disparity maps. Experiments on real-world datasets demonstrate the superiority of the proposed network over state-of-the-art methods. The code and dataset are available at https://mingyuan-lin.github.io/St-ED web/.

show abstract

Self-Supervised Depth Estimation Based on the Consistency of Synthetic-real Image Prediction

Tong,

Gao,

et al. 2023

2023 International Conference on Advanced Robotics and Mechatronics (ICARM)

View full text Add to dashboard Cite

The Farther the Better: Balanced Stereo Matching via Depth-Based Sampling and Adaptive Feature Refinement

Cited by 6 publications

References 59 publications

RobustMVS: Single Domain Generalized Deep Multi-View Stereo

RobustMVS: Single Domain Generalized Deep Multi-View Stereo

Learning Event-Based Motion Deblurring

Self-Supervised Depth Estimation Based on the Consistency of Synthetic-real Image Prediction

Contact Info

Product

Resources

About