{"ID":23475036,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.19747","arxiv_id":"2609.19747","title":"STAR: Structure-aware Test-time Adaptation for diffusion-based light field Reconstruction","abstract":"Light field (LF) reconstruction from limited and noisy focal stack (FS) measurements is a highly ill-posed inverse problem. Although the LF-to-FS imaging geometry is fixed for a given optical setup, LF spatial-angular structure---including within-view spatial details, cross-view angular dependencies, and disparity across views---varies across scenes. Consequently, a fixed pre-trained prior may not optimally capture the spatial-angular structure of each test LF. We propose Structure-aware Test-time Adaptation for diffusion-based light field Reconstruction (STAR), the first test-time adaptation framework for reconstructing an LF from FS. For each test LF, STAR freezes a pre-trained diffusion prior and fits three lightweight adapters to the observed FS to jointly adapt the three components of the LF's spatial-angular structure. STAR outperforms existing state-of-the-art methods in both two- and three-focal-sheet settings, with shorter inference times than those with test-time parameter updates.","short_abstract":"Light field (LF) reconstruction from limited and noisy focal stack (FS) measurements is a highly ill-posed inverse problem. Although the LF-to-FS imaging geometry is fixed for a given optical setup, LF spatial-angular structure---including within-view spatial details, cross-view angular dependencies, and disparity acro...","url_abs":"https://arxiv.org/abs/2609.19747","url_pdf":"https://arxiv.org/pdf/2609.19747v1","authors":"[\"Wontae Choi\",\"Ki Ryum Moon\",\"Jae Young Lee\",\"Hyung Sup Yun\",\"Il Yong Chun\"]","published":"2026-09-17T06:18:08Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}