Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation

TL;DR

This paper introduces Dr. Mo, a method that accelerates diffusion-based video generation by leveraging inter-frame motion consistency to reduce redundant computations, while maintaining high visual quality.

Contribution

The paper proposes a novel approach that propagates coarse noises across frames using motion cues, combined with a meta-network to adaptively select denoising steps, improving efficiency and quality.

Findings

Significantly faster video generation with maintained quality.

Effective motion-based noise propagation reduces computational redundancy.

Adaptive step selection balances efficiency and visual fidelity.

Abstract

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.