{"ID":2883241,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.08900","arxiv_id":"2508.08900","title":"DSER: Spectral Epipolar Representation for Efficient Light Field Depth Estimation","abstract":"Dense light field depth estimation remains challenging due to sparse angular sampling, occlusion boundaries, textureless regions, and the cost of exhaustive multi-view matching. We propose \\emph{Deep Spectral Epipolar Representation} (DSER), a geometry-aware framework that introduces spectral regularization in the epipolar domain for dense disparity reconstruction. DSER models frequency-consistent EPI structure to constrain correspondence estimation and couples this prior with a hybrid inference pipeline that combines least squares gradient initialization, plane-sweeping cost aggregation, and multiscale EPI refinement. An occlusion-aware directed random walk further propagates reliable disparity along edge-consistent paths, improving boundary sharpness and weak-texture stability. Experiments on benchmark and real-world light field datasets show that DSER achieves a strong accuracy-efficiency trade-off, producing more structurally consistent depth maps than representative classical and hybrid baselines. These results establish spectral epipolar regularization as an effective inductive bias for scalable and noise-robust light field depth estimation.","short_abstract":"Dense light field depth estimation remains challenging due to sparse angular sampling, occlusion boundaries, textureless regions, and the cost of exhaustive multi-view matching. We propose \\emph{Deep Spectral Epipolar Representation} (DSER), a geometry-aware framework that introduces spectral regularization in the epip...","url_abs":"https://arxiv.org/abs/2508.08900","url_pdf":"https://arxiv.org/pdf/2508.08900v4","authors":"[\"Noor Islam S. Mohammad\",\"Md Muntaqim Meherab\"]","published":"2025-08-12T12:41:47Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}