{"ID":6620554,"CreatedAt":"2026-07-15T01:01:48.440468303Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.12495","arxiv_id":"2607.12495","title":"RealSkin: Spatio-Spectral Partial Neural Adjoint Maps for Image-to-3D Attribute Transfer","abstract":"Creating photorealistic 3D assets requires bridging the appearance gap between real-world observations and synthetic models. A promising approach is to transfer visual attributes from real images onto synthetic 3D surfaces. Traditional methods struggle with resolution mismatch and the inherent discreteness of point correspondences. In contrast, resolution-robust functional maps enable smooth attribute propagation but rely on near-isometry assumptions and topological consistency. To address these limitations, we propose RealSkin, a self-supervised framework that performs correspondence optimization in a learned spectral domain, guided by spatial correspondences. We first introduce a spatial-guided registration algorithm to establish coarse correspondences under severe topological discrepancies. To relax strict isometric assumptions and handle partial correspondences, we further design a spectral-aware neural adjoint network that incorporates partial correspondences into a neural function space and models non-isometric residuals for correspondence refinement. Experimental results demonstrate that our method achieves state-of-the-art performance on challenging real-to-synthetic scenarios. The code will be publicly released.","short_abstract":"Creating photorealistic 3D assets requires bridging the appearance gap between real-world observations and synthetic models. A promising approach is to transfer visual attributes from real images onto synthetic 3D surfaces. Traditional methods struggle with resolution mismatch and the inherent discreteness of point cor...","url_abs":"https://arxiv.org/abs/2607.12495","url_pdf":"https://arxiv.org/pdf/2607.12495v1","authors":"[\"Jing Li\",\"Yawei Luo\",\"Xiangze Meng\",\"Ying Li\",\"Tieru Wu\",\"Rui Ma\"]","published":"2026-07-14T08:27:28Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}