{"ID":2838313,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18120","arxiv_id":"2511.18120","title":"MVS-TTA: Test-Time Adaptation for Multi-View Stereo via Meta-Auxiliary Learning","abstract":"Recent learning-based multi-view stereo (MVS) methods are data-driven and have achieved remarkable progress due to large-scale training data and advanced architectures. However, their generalization remains sub-optimal due to fixed model parameters trained on limited training data distributions. In contrast, optimization-based methods enable scene-specific adaptation but lack scalability and require costly per-scene optimization. In this paper, we propose MVS-TTA, an efficient test-time adaptation (TTA) framework that enhances the adaptability of learning-based MVS methods by bridging these two paradigms. Specifically, MVS-TTA employs a self-supervised, cross-view consistency loss as an auxiliary task to guide inference-time adaptation. We introduce a meta-auxiliary learning strategy to train the model to benefit from auxiliary-task-based updates explicitly. Our framework is model-agnostic and can be applied to a wide range of MVS methods with minimal architectural changes. Extensive experiments on standard datasets (DTU, BlendedMVS) and a challenging cross-dataset generalization setting demonstrate that MVS-TTA consistently improves performance, even when applied to state-of-the-art MVS models. To our knowledge, this is the first attempt to integrate optimization-based test-time adaptation into learning-based MVS using meta-learning. The code will be available at https://github.com/mart87987-svg/MVS-TTA.","short_abstract":"Recent learning-based multi-view stereo (MVS) methods are data-driven and have achieved remarkable progress due to large-scale training data and advanced architectures. However, their generalization remains sub-optimal due to fixed model parameters trained on limited training data distributions. In contrast, optimizati...","url_abs":"https://arxiv.org/abs/2511.18120","url_pdf":"https://arxiv.org/pdf/2511.18120v1","authors":"[\"Hannuo Zhang\",\"Zhixiang Chi\",\"Yang Wang\",\"Xinxin Zuo\"]","published":"2025-11-22T16:52:47Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":606757,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2838313,"paper_url":"https://arxiv.org/abs/2511.18120","paper_title":"MVS-TTA: Test-Time Adaptation for Multi-View Stereo via Meta-Auxiliary Learning","repo_url":"https://github.com/mart87987-svg/MVS-TTA","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}