CMD: ステレオマッチングのドメイン適応におけるマルチモーダル分布の制約
CMD: Constraining Multimodal Distribution for Domain Adaptation in Stereo Matching
教師なしドメイン適応で問題となるマルチモーダルな視差分布を、不確実性正則化と異方性ソフトargminで単峰化し、合成から実世界への汎化性能を向上させた。
著者: Zhelun Shen, Zhuo Li, Chenming Wu, Zhibo Rao, Lina Liu, Yuchao Dai, Liangjun Zhang
分類: cs.CV, cs.RO
原文アブストラクト
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}.
