{"ID":2830855,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.09925","arxiv_id":"2512.09925","title":"GAINS: Gaussian-based Inverse Rendering from Sparse Multi-View Captures","abstract":"Recent advances in Gaussian Splatting-based inverse rendering extend Gaussian primitives with shading parameters and physically grounded light transport, enabling high-quality material recovery from dense multi-view captures. However, these methods degrade sharply under sparse-view settings, where limited observations lead to severe ambiguity between geometry, reflectance, and lighting. We introduce GAINS (Gaussian-based Inverse rendering from Sparse multi-view captures), a two-stage inverse rendering framework that leverages learning-based priors to stabilize geometry and material estimation. GAINS first refines geometry using monocular depth/normal and diffusion priors, then employs segmentation, intrinsic image decomposition (IID), and diffusion priors to regularize material recovery. Extensive experiments on synthetic and real-world datasets show that GAINS significantly improves material parameter accuracy, relighting quality, and novel-view synthesis compared to state-of-the-art Gaussian-based inverse rendering methods, especially under sparse-view settings. Project page: https://patrickbail.github.io/gains/","short_abstract":"Recent advances in Gaussian Splatting-based inverse rendering extend Gaussian primitives with shading parameters and physically grounded light transport, enabling high-quality material recovery from dense multi-view captures. However, these methods degrade sharply under sparse-view settings, where limited observations...","url_abs":"https://arxiv.org/abs/2512.09925","url_pdf":"https://arxiv.org/pdf/2512.09925v1","authors":"[\"Patrick Noras\",\"Jun Myeong Choi\",\"Didier Stricker\",\"Pieter Peers\",\"Roni Sengupta\"]","published":"2025-12-10T18:58:11Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}