Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation
This addresses efficiency bottlenecks for researchers and practitioners using video diffusion models, representing an incremental improvement.
The paper tackles the high computational cost of diffusion-based video generation by proposing Dr. Mo, which exploits motion consistency in coarse-grained noises to propagate them across frames, reducing redundancy. It achieves substantial acceleration in video generation and editing tasks while improving visual quality.
Video generation using diffusion-based models is constrained by high computational costs due to the frame-wise iterative diffusion process. This work presents a Diffusion Reuse MOtion (Dr. Mo) network to accelerate latent video generation. Our key discovery is that coarse-grained noises in earlier denoising steps have demonstrated high motion consistency across consecutive video frames. Following this observation, Dr. Mo propagates those coarse-grained noises onto the next frame by incorporating carefully designed, lightweight inter-frame motions, eliminating massive computational redundancy in frame-wise diffusion models. The more sensitive and fine-grained noises are still acquired via later denoising steps, which can be essential to retain visual qualities. As such, deciding which intermediate steps should switch from motion-based propagations to denoising can be a crucial problem and a key tradeoff between efficiency and quality. Dr. Mo employs a meta-network named Denoising Step Selector (DSS) to dynamically determine desirable intermediate steps across video frames. Extensive evaluations on video generation and editing tasks have shown that Dr. Mo can substantially accelerate diffusion models in video tasks with improved visual qualities.