Underwater Depth Estimation via Stereo Adaptation Networks

Ye, Xinchen; Zhang, Jinyi; Yuan, Yazhi; Xu, Rui; Wang, Zhihui; Li, Haojie

doi:10.1109/tcsvt.2023.3249223

Cited by 5 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To handle the domain discrepancy, a common approach is to adapt the source domain distribution to the target domain distribution via domain adaptation (DA) techniques [17]- [20]. Whereas, it requires access to unlabeled samples in target domains, which limits their applicability in our MVS generalization task.…”

Section: Introductionmentioning

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: Introductionmentioning

confidence: 99%