{"ID":2824459,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.23667","arxiv_id":"2512.23667","title":"IDT: A Physically Grounded Transformer for Feed-Forward Multi-View Intrinsic Decomposition","abstract":"Intrinsic image decomposition is fundamental for visual understanding, as RGB images entangle material properties, illumination, and view-dependent effects. Recent diffusion-based methods have achieved strong results for single-view intrinsic decomposition; however, extending these approaches to multi-view settings remains challenging, often leading to severe view inconsistency. We propose \\textbf{Intrinsic Decomposition Transformer (IDT)}, a feed-forward framework for multi-view intrinsic image decomposition. By leveraging transformer-based attention to jointly reason over multiple input images, IDT produces view-consistent intrinsic factors in a single forward pass, without iterative generative sampling. IDT adopts a physically grounded image formation model that explicitly decomposes images into diffuse reflectance, diffuse shading, and specular shading. This structured factorization separates Lambertian and non-Lambertian light transport, enabling interpretable and controllable decomposition of material and illumination effects across views. Experiments on both synthetic and real-world datasets demonstrate that IDT achieves cleaner diffuse reflectance, more coherent diffuse shading, and better-isolated specular components, while substantially improving multi-view consistency compared to prior intrinsic decomposition methods.","short_abstract":"Intrinsic image decomposition is fundamental for visual understanding, as RGB images entangle material properties, illumination, and view-dependent effects. Recent diffusion-based methods have achieved strong results for single-view intrinsic decomposition; however, extending these approaches to multi-view settings rem...","url_abs":"https://arxiv.org/abs/2512.23667","url_pdf":"https://arxiv.org/pdf/2512.23667v2","authors":"[\"Kang Du\",\"Yirui Guan\",\"Zeyu Wang\"]","published":"2025-12-29T18:24:46Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}