{"ID":5675433,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-07T01:06:03.009715918Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.02301","arxiv_id":"2607.02301","title":"InvSplat: Inverse Feed-Forward Scene Splatting","abstract":"Inverse rendering aims to recover both 3D geometry and physically meaningful material properties from images, enabling applications such as relighting and novel view synthesis. Optimization-based methods achieve high fidelity but require costly per-scene fitting, while image-space learning-based approaches often suffer from multi-view inconsistencies and lack an explicit 3D representation for stable novel view rendering. We present a feed-forward multi-view reconstruction framework for inverse rendering that directly predicts a structured 3D Gaussian representation with intrinsic material attributes. Each Gaussian primitive is parameterized by mean, normal, opacity, rotation, scale, albedo, metallic, and roughness, enabling a disentangled and physically grounded scene representation. Our model integrates priors from a material estimation network with a multi-view 3D reconstruction backbone, allowing joint prediction of geometry and reflectance parameters in a single forward pass. Experiments on synthetic and real-world datasets demonstrate improved multi-view consistency compared to 2D baselines, accurate material recovery, and stable novel view rendering. Our representation further supports physically-based relighting and more faithful modeling of view-dependent effects compared to existing RGB-based feed-forward reconstruction methods. Our project webpage is: $\\href{https://poliik.github.io/invsplat/}{\\text{https://poliik.github.io/invsplat/}}$.","short_abstract":"Inverse rendering aims to recover both 3D geometry and physically meaningful material properties from images, enabling applications such as relighting and novel view synthesis. Optimization-based methods achieve high fidelity but require costly per-scene fitting, while image-space learning-based approaches often suffer...","url_abs":"https://arxiv.org/abs/2607.02301","url_pdf":"https://arxiv.org/pdf/2607.02301v1","authors":"[\"Polina Karpikova\",\"Wenjing Bian\",\"Haofei Xu\",\"Hendrik Lensch\",\"Andreas Geiger\"]","published":"2026-07-02T15:18:08Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}