2025/06/05 by Huihan Wang, Zhiwen Yang, Wang, Huihan +9
Computer Science · #Channel (broadcasting) #Consistency (knowledge bases) #Face recognition and analysis #Generative Adversarial Networks and Image Synthesis #Human Pose and Action Recognition #Key (lock) #Noise (video) #Noise reduction #Residual
paper · pdf · doi:10.48550/arxiv.2506.04956
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/06/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.