Article Dans Une Revue Proceedings of the ACM on Computer Graphics and Interactive Techniques Année : 2026

Intrinsic decomposition and editing of 3D Gaussian splats

Résumé

albedo (a) Input radiance field (b) Intrinsic editing (c) Edited radiance field (c) Edited radiance field, other viewpoint Fig. 1. By decoupling albedo and shading in a radiance field (a-b) our method enables direct edition of albedo in a physically plausible way while remaining multi-view consistent (c-d). Intrinsic decomposition -which expresses image colors as the product of diffuse albedo and shading, possibly augmented with view-dependent residuals -has a long history in image editing as it enables the modification of object colors and textures without altering lighting. We extend intrinsic decomposition to radiance fields represented with Gaussian splatting by proposing solutions to three key aspects of such decomposition. First, we describe how to model the intrinsic decomposition as independent sets of Gaussian primitives, which allows each set to adapt to the characteristics of the layer it represents. Second, we present an optimization procedure guided by data-driven predictions to disentangle multi-view photographs of a scene into the aforementioned intrinsic sets. Finally, we provide an editing workflow where users modify the texture of planar surfaces simply by modifying the albedo of that surface in one image. Capturing this edit within the intrinsic radiance field allows re-rendering of the edited scene with plausible lighting under arbitrary viewpoints.

Fichier principal
Vignette du fichier
paper_authors_version.pdf (76.86 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05602203 , version 1 (04-05-2026)

Licence

Identifiants

Citer

Alexandre Lanvin, Simon Lucas, Jeffrey Hu, Adrien Bousseau, George Drettakis. Intrinsic decomposition and editing of 3D Gaussian splats. Proceedings of the ACM on Computer Graphics and Interactive Techniques, 2026, ⟨10.1145/3804495⟩. ⟨hal-05602203⟩
0 Consultations
4 Téléchargements

Altmetric

Partager

  • More