TPDiff: Temporal Pyramid Video Diffusion Model
원문 초록
The development of video diffusion models unveils a significant challenge: the substantial computational demands. To mitigate this challenge, we note that the reverse process of diffusion exhibits an inherent entropy-reducing nature. Given the inter-frame redundancy in video modality, maintaining full frame rates in high-entropy stages is unnecessary. Based on this insight, we propose TPDiff, a unified framework to enhance training and inference efficiency. By dividing diffusion into several stages, our framework progressively increases frame rate along the diffusion process with only the last stage operating on full frame rate, thereby optimizing computational efficiency. To train the multi-stage diffusion model, we introduce a dedicated training framework: stage-wise diffusion. By solving the partitioned probability flow ordinary differential equations (ODE) of diffusion under aligned data and noise, our training strategy is applicable to various diffusion forms and further enhances training efficiency. Comprehensive experimental evaluations validate the generality of our method, demonstrating 50% reduction in training cost and 1.5x improvement in inference efficiency.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sparse Imagination for Efficient Visual World Model Planning
TriLiteNet: Lightweight Model for Multi-Task Visual Perception
Making Language Model a Hierarchical Classifier and Generator
From Roots to Rewards: Dynamic Tree Reasoning with RL
DCR: Quantifying Data Contamination in LLMs Evaluation
U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV
토론
이 논문과 연결된 포럼 글이 아직 없습니다.