Sync4D: Video Guided Controllable Dynamics for Physics-Based 4D Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913420248350720 |
|---|---|
| author | Fu, Zhoujie Wei, Jiacheng Shen, Wenhao Song, Chaoyue Yang, Xiaofeng Liu, Fayao Yang, Xulei Lin, Guosheng |
| author_facet | Fu, Zhoujie Wei, Jiacheng Shen, Wenhao Song, Chaoyue Yang, Xiaofeng Liu, Fayao Yang, Xulei Lin, Guosheng |
| contents | In this work, we introduce a novel approach for creating controllable dynamics in 3D-generated Gaussians using casually captured reference videos. Our method transfers the motion of objects from reference videos to a variety of generated 3D Gaussians across different categories, ensuring precise and customizable motion transfer. We achieve this by employing blend skinning-based non-parametric shape reconstruction to extract the shape and motion of reference objects. This process involves segmenting the reference objects into motion-related parts based on skinning weights and establishing shape correspondences with generated target shapes. To address shape and temporal inconsistencies prevalent in existing methods, we integrate physical simulation, driving the target shapes with matched motion. This integration is optimized through a displacement loss to ensure reliable and genuine dynamics. Our approach supports diverse reference inputs, including humans, quadrupeds, and articulated objects, and can generate dynamics of arbitrary length, providing enhanced fidelity and applicability. Unlike methods heavily reliant on diffusion video generation models, our technique offers specific and high-quality motion transfer, maintaining both shape integrity and temporal consistency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_16849 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Sync4D: Video Guided Controllable Dynamics for Physics-Based 4D Generation Fu, Zhoujie Wei, Jiacheng Shen, Wenhao Song, Chaoyue Yang, Xiaofeng Liu, Fayao Yang, Xulei Lin, Guosheng Computer Vision and Pattern Recognition In this work, we introduce a novel approach for creating controllable dynamics in 3D-generated Gaussians using casually captured reference videos. Our method transfers the motion of objects from reference videos to a variety of generated 3D Gaussians across different categories, ensuring precise and customizable motion transfer. We achieve this by employing blend skinning-based non-parametric shape reconstruction to extract the shape and motion of reference objects. This process involves segmenting the reference objects into motion-related parts based on skinning weights and establishing shape correspondences with generated target shapes. To address shape and temporal inconsistencies prevalent in existing methods, we integrate physical simulation, driving the target shapes with matched motion. This integration is optimized through a displacement loss to ensure reliable and genuine dynamics. Our approach supports diverse reference inputs, including humans, quadrupeds, and articulated objects, and can generate dynamics of arbitrary length, providing enhanced fidelity and applicability. Unlike methods heavily reliant on diffusion video generation models, our technique offers specific and high-quality motion transfer, maintaining both shape integrity and temporal consistency. |
| title | Sync4D: Video Guided Controllable Dynamics for Physics-Based 4D Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.16849 |