AI Paper Atlas

Research map / Video / Video generation

LaMD: Latent Motion Diffusion for Image-Conditional Video Generation

Yaosi Hu, Zhenzhong Chen, Chong Luo

IJCV 2025 · Video › Video generation · approach: Efficient video diffusion models · 43 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
raise motion channel size from d=1 to d=3 (ablation)MCD-VAE · BAIR reconstructionFVD: 41.91 -> 36.05Improved
raise motion channel size from d=3 to d=4 (ablation)MCD-VAE · BAIR reconstructionFVD: 36.05 -> 38.84Hurt
keep a temporal dimension in latent motion (d_t=2, d=2) instead of removing it (ablation)MCD-VAE · BAIR reconstructionFVD: 36.05 -> 37.93No clear effect
use larger latent space (beta e-5, d=4) instead of smaller (beta e-2, d=3) (ablation)LaMD · Landscape generationFVD: 100.7 -> 127.1Hurt
use larger latent space (beta e-5, d=4) instead of smaller (beta e-2, d=3) (ablation)MCD-VAE · Landscape reconstructionFVD: 58.59 -> 37.35Improved
MCD-VAE motion-decomposed autoencoder instead of VQGANvideo autoencoder · BAIR reconstructionFVD: 42.80 -> 36.05Improved
generate latent motion with 2D-UNet (LaMD) instead of flow sequence with 3D-UNet (LFDM)latent motion diffusion · 128-frame 128x128 samplingsampling time (s): 40.1s -> 10.7sImproved
latent motion diffusion instead of latent video diffusionLVDM · 128-frame 128x128 samplingsampling time (s): 26.6s -> 10.7sImproved
LaMD compared with open-domain DynamiCrafter on dynamicsLaMD · Landscape motion qualitydynamic degree: 94.60% vs 55.13%Hurt
LaMD instead of cINN on motion smoothnessLaMD · Landscape motion qualitymotion smoothness: 99.41% -> 99.47%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy