LaMD: Latent Motion Diffusion for Image-Conditional Video Generation

TL;DR

LaMD introduces a latent motion diffusion framework that simplifies video generation by focusing on motion modeling, resulting in high-quality, controllable videos with faster sampling across diverse datasets.

Contribution

The paper presents a novel latent motion diffusion approach combining a motion autoencoder and diffusion generator to improve efficiency and expressiveness in video generation.

Findings

High-quality video generation on multiple benchmarks

Significant reduction in sampling time

Effective modeling of diverse and controllable motions

Abstract

The video generation field has witnessed rapid improvements with the introduction of recent diffusion models. While these models have successfully enhanced appearance quality, they still face challenges in generating coherent and natural movements while efficiently sampling videos. In this paper, we propose to condense video generation into a problem of motion generation, to improve the expressiveness of motion and make video generation more manageable. This can be achieved by breaking down the video generation process into latent motion generation and video reconstruction. Specifically, we present a latent motion diffusion (LaMD) framework, which consists of a motion-decomposed video autoencoder and a diffusion-based motion generator, to implement this idea. Through careful design, the motion-decomposed video autoencoder can compress patterns in movement into a concise latent motion representation. Consequently, the diffusion-based motion generator is able to efficiently generate realistic motion on a continuous latent space under multi-modal conditions, at a cost that is similar to that of image diffusion models. Results show that LaMD generates high-quality videos on various benchmark datasets, including BAIR, Landscape, NATOPS, MUG and CATER-GEN, that encompass a variety of stochastic dynamics and highly controllable movements on multiple image-conditional video generation tasks, while significantly decreases sampling time.