選択的Mixture-of-Expertsによる実世界でのロバストなステレオマッチング学習
Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts
視覚基盤モデルをLoRAとMixture-of-Expertsで効率的に適応させ、シーンに応じて専門家を選択することで、ドメインシフトに強いステレオマッチングを実現した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Yun Wang, Longguang Wang, Chenghao Zhang, Yongjian Zhang, Zhanjie Zhang, Ao Ma, Chenyou Fan, Tin Lun Lam, Junjie Hu
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
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 distributions among diverse datasets. Leveraging Vision Foundation Models (VFMs) can intuitively enhance the model's robustness, but integrating such a model into stereo matching cost-effectively to fully realize their robustness remains a key challenge. To address this, we propose SMoEStereo, a novel framework that adapts VFMs for stereo matching through a tailored, scene-specific fusion of Low-Rank Adaptation (LoRA) and Mixture-of-Experts (MoE) modules. SMoEStereo introduces MoE-LoRA with adaptive ranks and MoE-Adapter with adaptive kernel sizes. The former dynamically selects optimal experts within MoE to adapt varying scenes across domains, while the latter injects inductive bias into frozen VFMs to improve geometric feature extraction. Importantly, to mitigate computational overhead, we further propose a lightweight decision network that selectively activates MoE modules based on input complexity, balancing efficiency with accuracy. Extensive experiments demonstrate that our method exhibits state-of-the-art cross-domain and joint generalization across multiple benchmarks without dataset-specific adaptation. The code is available at \textcolor{red}{https://github.com/cocowy1/SMoE-Stereo}.
