Style4D-Bench: A Benchmark Suite for 4D Stylization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Beiqi, Shao, Shuai, Feng, Haitang, Lai, Jianhuang, Si, Jianlou, Wang, Guangcong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912555547492352
author Chen, Beiqi
Shao, Shuai
Feng, Haitang
Lai, Jianhuang
Si, Jianlou
Wang, Guangcong
author_facet Chen, Beiqi
Shao, Shuai
Feng, Haitang
Lai, Jianhuang
Si, Jianlou
Wang, Guangcong
contents We introduce Style4D-Bench, the first benchmark suite specifically designed for 4D stylization, with the goal of standardizing evaluation and facilitating progress in this emerging area. Style4D-Bench comprises: 1) a comprehensive evaluation protocol measuring spatial fidelity, temporal coherence, and multi-view consistency through both perceptual and quantitative metrics, 2) a strong baseline that make an initial attempt for 4D stylization, and 3) a curated collection of high-resolution dynamic 4D scenes with diverse motions and complex backgrounds. To establish a strong baseline, we present Style4D, a novel framework built upon 4D Gaussian Splatting. It consists of three key components: a basic 4DGS scene representation to capture reliable geometry, a Style Gaussian Representation that leverages lightweight per-Gaussian MLPs for temporally and spatially aware appearance control, and a Holistic Geometry-Preserved Style Transfer module designed to enhance spatio-temporal consistency via contrastive coherence learning and structural content preservation. Extensive experiments on Style4D-Bench demonstrate that Style4D achieves state-of-the-art performance in 4D stylization, producing fine-grained stylistic details with stable temporal dynamics and consistent multi-view rendering. We expect Style4D-Bench to become a valuable resource for benchmarking and advancing research in stylized rendering of dynamic 3D scenes. Project page: https://becky-catherine.github.io/Style4D . Code: https://github.com/Becky-catherine/Style4D-Bench .
format Preprint
id arxiv_https___arxiv_org_abs_2508_19243
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Style4D-Bench: A Benchmark Suite for 4D Stylization
Chen, Beiqi
Shao, Shuai
Feng, Haitang
Lai, Jianhuang
Si, Jianlou
Wang, Guangcong
Computer Vision and Pattern Recognition
We introduce Style4D-Bench, the first benchmark suite specifically designed for 4D stylization, with the goal of standardizing evaluation and facilitating progress in this emerging area. Style4D-Bench comprises: 1) a comprehensive evaluation protocol measuring spatial fidelity, temporal coherence, and multi-view consistency through both perceptual and quantitative metrics, 2) a strong baseline that make an initial attempt for 4D stylization, and 3) a curated collection of high-resolution dynamic 4D scenes with diverse motions and complex backgrounds. To establish a strong baseline, we present Style4D, a novel framework built upon 4D Gaussian Splatting. It consists of three key components: a basic 4DGS scene representation to capture reliable geometry, a Style Gaussian Representation that leverages lightweight per-Gaussian MLPs for temporally and spatially aware appearance control, and a Holistic Geometry-Preserved Style Transfer module designed to enhance spatio-temporal consistency via contrastive coherence learning and structural content preservation. Extensive experiments on Style4D-Bench demonstrate that Style4D achieves state-of-the-art performance in 4D stylization, producing fine-grained stylistic details with stable temporal dynamics and consistent multi-view rendering. We expect Style4D-Bench to become a valuable resource for benchmarking and advancing research in stylized rendering of dynamic 3D scenes. Project page: https://becky-catherine.github.io/Style4D . Code: https://github.com/Becky-catherine/Style4D-Bench .
title Style4D-Bench: A Benchmark Suite for 4D Stylization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.19243