Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2511.17185 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914615103848448 |
|---|---|
| author | Chen, Yipeng Ye, Zhichao Fang, Zhenzhou Chen, Xinyu Zhang, Xiaoyu Liu, Jialing Wang, Nan Zhang, Guofeng Liu, Haomin |
| author_facet | Chen, Yipeng Ye, Zhichao Fang, Zhenzhou Chen, Xinyu Zhang, Xiaoyu Liu, Jialing Wang, Nan Zhang, Guofeng Liu, Haomin |
| contents | We propose PostCam, a streamlined framework for novel-view video generation that achieves superior detail preservation and precise camera trajectory editing in dynamic scenes. Current methods often struggle with a trade-off between pose-based control, which lacks visual detail, and rendering-based guidance, which is overly sensitive to geometric accuracy. Despite recent hybrid attempts, achieving precise motion and visual consistency remains challenging due to the lack of effective cross-modal alignment. We argue that robust control stems from the deep alignment of multimodal signals rather than increased input complexity. Our core contribution is the Query-Shared Cross-Attention mechanism, which projects 6-DoF poses and rendered features into a unified latent space. This allows the model to spontaneously achieve intrinsic consistency between motion cues and pixel-level guidance during denoising. Experiments demonstrate that PostCam maintains high-fidelity visual details while outperforming state-of-the-art methods by 20% in trajectory precision, exhibiting superior robustness in complex dynamic scenes. Our project webpage is publicly available at: https://cccqaq.github.io/PostCam.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_17185 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention Chen, Yipeng Ye, Zhichao Fang, Zhenzhou Chen, Xinyu Zhang, Xiaoyu Liu, Jialing Wang, Nan Zhang, Guofeng Liu, Haomin Computer Vision and Pattern Recognition We propose PostCam, a streamlined framework for novel-view video generation that achieves superior detail preservation and precise camera trajectory editing in dynamic scenes. Current methods often struggle with a trade-off between pose-based control, which lacks visual detail, and rendering-based guidance, which is overly sensitive to geometric accuracy. Despite recent hybrid attempts, achieving precise motion and visual consistency remains challenging due to the lack of effective cross-modal alignment. We argue that robust control stems from the deep alignment of multimodal signals rather than increased input complexity. Our core contribution is the Query-Shared Cross-Attention mechanism, which projects 6-DoF poses and rendered features into a unified latent space. This allows the model to spontaneously achieve intrinsic consistency between motion cues and pixel-level guidance during denoising. Experiments demonstrate that PostCam maintains high-fidelity visual details while outperforming state-of-the-art methods by 20% in trajectory precision, exhibiting superior robustness in complex dynamic scenes. Our project webpage is publicly available at: https://cccqaq.github.io/PostCam.github.io/ |
| title | PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.17185 |