{"ID":2872169,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.09352","arxiv_id":"2509.09352","title":"Texture-aware Intrinsic Image Decomposition with Model- and Learning-based Priors","abstract":"This paper aims to recover the intrinsic reflectance layer and shading layer given a single image. Though this intrinsic image decomposition problem has been studied for decades, it remains a significant challenge in cases of complex scenes, i.e. spatially-varying lighting effect and rich textures. In this paper, we propose a novel method for handling severe lighting and rich textures in intrinsic image decomposition, which enables to produce high-quality intrinsic images for real-world images. Specifically, we observe that previous learning-based methods tend to produce texture-less and over-smoothing intrinsic images, which can be used to infer the lighting and texture information given a RGB image. In this way, we design a texture-guided regularization term and formulate the decomposition problem into an optimization framework, to separate the material textures and lighting effect. We demonstrate that combining the novel texture-aware prior can produce superior results to existing approaches.","short_abstract":"This paper aims to recover the intrinsic reflectance layer and shading layer given a single image. Though this intrinsic image decomposition problem has been studied for decades, it remains a significant challenge in cases of complex scenes, i.e. spatially-varying lighting effect and rich textures. In this paper, we pr...","url_abs":"https://arxiv.org/abs/2509.09352","url_pdf":"https://arxiv.org/pdf/2509.09352v1","authors":"[\"Xiaodong Wang\",\"Zijun He\",\"Xin Yuan\"]","published":"2025-09-11T11:07:25Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}