CMD: Constraining Multimodal Distribution for Domain Adaptation in Stereo Matching
Recently, learning-based stereo matching methods have achieved great improvement in public benchmarks, where soft argmin and smooth L1 loss play a core contribution to their success. However, in unsupervised domain adaptation scenarios, we observe that these two operations often yield multimodal disparity probability distributions in target domains, resulting in degraded generalization. In this paper, we propose a novel approach, Constrain Multi-modal Distribution (CMD), to address this issue. Specifically, we introduce \textit{uncertainty-regularized minimization} and \textit{anisotropic soft argmin} to encourage the network to produce predominantly unimodal disparity distributions in the target domain, thereby improving prediction accuracy. Experimentally, we apply the proposed method to multiple representative stereo-matching networks and conduct domain adaptation from synthetic data to unlabeled real-world scenes. Results consistently demonstrate improved generalization in both top-performing and domain-adaptable stereo-matching models. The code for CMD will be available at: \href{https://github.com/gallenszl/CMD}{https://github.com/gallenszl/CMD}.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationStereo MatchingUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
SR-Stereo & DAPE: Stepwise Regression and Pre-trained Edges for Practical Stereo Matching
Due to the difficulty in obtaining real samples and ground truth, the generalization performance and domain adaptation performance are critical for the feasibility of stereo matching methods in practical applications. Ho…
Disparity EstimationDomain AdaptationregressionStereo MatchingGradient Distribution Alignment Certificates Better Adversarial Domain Adaptation
The latest heuristic for handling the domain shift in unsupervised domain adaptation tasks is to reduce the data distribution discrepancy using adversarial learning. Recent studies improve the conventional adversaria…
Domain AdaptationUnsupervised Domain AdaptationLearning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts
Recently, learning-based stereo matching networks have advanced significantly. However, they often lack robustness and struggle to achieve impressive cross-domain performance due to domain shifts and imbalanced disparity…
Inductive BiasMixture-of-ExpertsStereo MatchingAdvances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models
In real-world scenarios, achieving domain adaptation and generalization poses significant challenges, as models must adapt to or generalize across unknown target distributions. Extending these capabilities to unseen mult…
Action RecognitionDomain AdaptationDomain GeneralizationSemantic Segmentation+1AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach
Recently, records on stereo matching benchmarks are constantly broken by end-to-end disparity networks. However, the domain adaptation ability of these deep models is quite limited. Addressing such problem, we present a …
Domain AdaptationStereo Matching