Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.07769 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917109519351808 |
|---|---|
| author | Liu, Xiaoyan Li, Kangrui Song, Yuehao Liu, Jiaxin |
| author_facet | Liu, Xiaoyan Li, Kangrui Song, Yuehao Liu, Jiaxin |
| contents | The synthesis of spatiotemporally coherent 4D content presents fundamental challenges in computer vision, requiring simultaneous modeling of high-fidelity spatial representations and physically plausible temporal dynamics. Current approaches often struggle to maintain view consistency while handling complex scene dynamics, particularly in large-scale environments with multiple interacting elements. This work introduces Dream4D, a novel framework that bridges this gap through a synergy of controllable video generation and neural 4D reconstruction. Our approach seamlessly combines a two-stage architecture: it first predicts optimal camera trajectories from a single image using few-shot learning, then generates geometrically consistent multi-view sequences via a specialized pose-conditioned diffusion process, which are finally converted into a persistent 4D representation. This framework is the first to leverage both rich temporal priors from video diffusion models and geometric awareness of the reconstruction models, which significantly facilitates 4D generation and shows higher quality (e.g., mPSNR, mSSIM) over existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07769 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dream4D: Lifting Camera-Controlled I2V towards Spatiotemporally Consistent 4D Generation Liu, Xiaoyan Li, Kangrui Song, Yuehao Liu, Jiaxin Computer Vision and Pattern Recognition The synthesis of spatiotemporally coherent 4D content presents fundamental challenges in computer vision, requiring simultaneous modeling of high-fidelity spatial representations and physically plausible temporal dynamics. Current approaches often struggle to maintain view consistency while handling complex scene dynamics, particularly in large-scale environments with multiple interacting elements. This work introduces Dream4D, a novel framework that bridges this gap through a synergy of controllable video generation and neural 4D reconstruction. Our approach seamlessly combines a two-stage architecture: it first predicts optimal camera trajectories from a single image using few-shot learning, then generates geometrically consistent multi-view sequences via a specialized pose-conditioned diffusion process, which are finally converted into a persistent 4D representation. This framework is the first to leverage both rich temporal priors from video diffusion models and geometric awareness of the reconstruction models, which significantly facilitates 4D generation and shows higher quality (e.g., mPSNR, mSSIM) over existing methods. |
| title | Dream4D: Lifting Camera-Controlled I2V towards Spatiotemporally Consistent 4D Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.07769 |