Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Hanzhou, Huang, Jia, Lu, Mi, Saripalli, Srikanth, Jiang, Peng
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2509.26455
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908856477548544
author Liu, Hanzhou
Huang, Jia
Lu, Mi
Saripalli, Srikanth
Jiang, Peng
author_facet Liu, Hanzhou
Huang, Jia
Lu, Mi
Saripalli, Srikanth
Jiang, Peng
contents We present Stylos, a single-forward 3D Gaussian framework for 3D style transfer that operates on unposed content, from a single image to a multi-view collection, conditioned on a separate reference style image. Stylos synthesizes a stylized 3D Gaussian scene without per-scene optimization or precomputed poses, achieving geometry-aware, view-consistent stylization that generalizes to unseen categories, scenes, and styles. At its core, Stylos adopts a Transformer backbone with two pathways: geometry predictions retain self-attention to preserve geometric fidelity, while style is injected via global cross-attention to enforce visual consistency across views. With the addition of a voxel-based 3D style loss that aligns aggregated scene features to style statistics, Stylos enforces view-consistent stylization while preserving geometry. Experiments across multiple datasets demonstrate that Stylos delivers high-quality zero-shot stylization, highlighting the effectiveness of global style-content coupling, the proposed 3D style loss, and the scalability of our framework from single view to large-scale multi-view settings. Our codes are available at https://github.com/HanzhouLiu/Stylos.
format Preprint
id arxiv_https___arxiv_org_abs_2509_26455
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stylos: Multi-View 3D Stylization with Single-Forward Gaussian Splatting
Liu, Hanzhou
Huang, Jia
Lu, Mi
Saripalli, Srikanth
Jiang, Peng
Computer Vision and Pattern Recognition
We present Stylos, a single-forward 3D Gaussian framework for 3D style transfer that operates on unposed content, from a single image to a multi-view collection, conditioned on a separate reference style image. Stylos synthesizes a stylized 3D Gaussian scene without per-scene optimization or precomputed poses, achieving geometry-aware, view-consistent stylization that generalizes to unseen categories, scenes, and styles. At its core, Stylos adopts a Transformer backbone with two pathways: geometry predictions retain self-attention to preserve geometric fidelity, while style is injected via global cross-attention to enforce visual consistency across views. With the addition of a voxel-based 3D style loss that aligns aggregated scene features to style statistics, Stylos enforces view-consistent stylization while preserving geometry. Experiments across multiple datasets demonstrate that Stylos delivers high-quality zero-shot stylization, highlighting the effectiveness of global style-content coupling, the proposed 3D style loss, and the scalability of our framework from single view to large-scale multi-view settings. Our codes are available at https://github.com/HanzhouLiu/Stylos.
title Stylos: Multi-View 3D Stylization with Single-Forward Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.26455