FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912415380144128 |
|---|---|
| author | Wang, Huihan Yang, Zhiwen Zhang, Hui Zhao, Dan Wei, Bingzheng Xu, Yan |
| author_facet | Wang, Huihan Yang, Zhiwen Zhang, Hui Zhao, Dan Wei, Bingzheng Xu, Yan |
| contents | Synthesizing high-quality dynamic medical videos remains a significant challenge due to the need for modeling both spatial consistency and temporal dynamics. Existing Transformer-based approaches face critical limitations, including insufficient channel interactions, high computational complexity from self-attention, and coarse denoising guidance from timestep embeddings when handling varying noise levels. In this work, we propose FEAT, a full-dimensional efficient attention Transformer, which addresses these issues through three key innovations: (1) a unified paradigm with sequential spatial-temporal-channel attention mechanisms to capture global dependencies across all dimensions, (2) a linear-complexity design for attention mechanisms in each dimension, utilizing weighted key-value attention and global channel attention, and (3) a residual value guidance module that provides fine-grained pixel-level guidance to adapt to different noise levels. We evaluate FEAT on standard benchmarks and downstream tasks, demonstrating that FEAT-S, with only 23\% of the parameters of the state-of-the-art model Endora, achieves comparable or even superior performance. Furthermore, FEAT-L surpasses all comparison methods across multiple datasets, showcasing both superior effectiveness and scalability. Code is available at https://github.com/Yaziwel/FEAT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_04956 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation Wang, Huihan Yang, Zhiwen Zhang, Hui Zhao, Dan Wei, Bingzheng Xu, Yan Computer Vision and Pattern Recognition Synthesizing high-quality dynamic medical videos remains a significant challenge due to the need for modeling both spatial consistency and temporal dynamics. Existing Transformer-based approaches face critical limitations, including insufficient channel interactions, high computational complexity from self-attention, and coarse denoising guidance from timestep embeddings when handling varying noise levels. In this work, we propose FEAT, a full-dimensional efficient attention Transformer, which addresses these issues through three key innovations: (1) a unified paradigm with sequential spatial-temporal-channel attention mechanisms to capture global dependencies across all dimensions, (2) a linear-complexity design for attention mechanisms in each dimension, utilizing weighted key-value attention and global channel attention, and (3) a residual value guidance module that provides fine-grained pixel-level guidance to adapt to different noise levels. We evaluate FEAT on standard benchmarks and downstream tasks, demonstrating that FEAT-S, with only 23\% of the parameters of the state-of-the-art model Endora, achieves comparable or even superior performance. Furthermore, FEAT-L surpasses all comparison methods across multiple datasets, showcasing both superior effectiveness and scalability. Code is available at https://github.com/Yaziwel/FEAT. |
| title | FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.04956 |