SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yao, Chun-Han, Xie, Yiming, Voleti, Vikram, Jiang, Huaizu, Jampani, Varun
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908282931642368
author Yao, Chun-Han
Xie, Yiming
Voleti, Vikram
Jiang, Huaizu
Jampani, Varun
author_facet Yao, Chun-Han
Xie, Yiming
Voleti, Vikram
Jiang, Huaizu
Jampani, Varun
contents We present Stable Video 4D 2.0 (SV4D 2.0), a multi-view video diffusion model for dynamic 3D asset generation. Compared to its predecessor SV4D, SV4D 2.0 is more robust to occlusions and large motion, generalizes better to real-world videos, and produces higher-quality outputs in terms of detail sharpness and spatio-temporal consistency. We achieve this by introducing key improvements in multiple aspects: 1) network architecture: eliminating the dependency of reference multi-views and designing blending mechanism for 3D and frame attention, 2) data: enhancing quality and quantity of training data, 3) training strategy: adopting progressive 3D-4D training for better generalization, and 4) 4D optimization: handling 3D inconsistency and large motion via 2-stage refinement and progressive frame sampling. Extensive experiments demonstrate significant performance gain by SV4D 2.0 both visually and quantitatively, achieving better detail (-14\% LPIPS) and 4D consistency (-44\% FV4D) in novel-view video synthesis and 4D optimization (-12\% LPIPS and -24\% FV4D) compared to SV4D. Project page: https://sv4d20.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16396
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation
Yao, Chun-Han
Xie, Yiming
Voleti, Vikram
Jiang, Huaizu
Jampani, Varun
Computer Vision and Pattern Recognition
We present Stable Video 4D 2.0 (SV4D 2.0), a multi-view video diffusion model for dynamic 3D asset generation. Compared to its predecessor SV4D, SV4D 2.0 is more robust to occlusions and large motion, generalizes better to real-world videos, and produces higher-quality outputs in terms of detail sharpness and spatio-temporal consistency. We achieve this by introducing key improvements in multiple aspects: 1) network architecture: eliminating the dependency of reference multi-views and designing blending mechanism for 3D and frame attention, 2) data: enhancing quality and quantity of training data, 3) training strategy: adopting progressive 3D-4D training for better generalization, and 4) 4D optimization: handling 3D inconsistency and large motion via 2-stage refinement and progressive frame sampling. Extensive experiments demonstrate significant performance gain by SV4D 2.0 both visually and quantitatively, achieving better detail (-14\% LPIPS) and 4D consistency (-44\% FV4D) in novel-view video synthesis and 4D optimization (-12\% LPIPS and -24\% FV4D) compared to SV4D. Project page: https://sv4d20.github.io.
title SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.16396