FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Huihan, Yang, Zhiwen, Zhang, Hui, Zhao, Dan, Wei, Bingzheng, Xu, Yan
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