AI Paper Atlas

Research map / Video / Video generation

EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer

Yuxiao Yang, Hualian Sheng, Sijia Cai, Jing Lin, Jiahao Wang, Bing Deng, Junzhe Lu, Haoqian Wang, Jieping Ye

ICLR 2026 · Video › Video generation · approach: Trajectory-guided motion control · 10 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
Add joint video-motion modeling (EchoMotion) vs Wan-5BWan-5B · Human T2V benchmarkHuman Anatomy: 83.0 -> 85.1Improved
Add joint video-motion modelingWan-5B · Human T2V benchmarkPosture Plausibility (human): 68.9 -> 81.6Improved
Add joint video-motion modelingWan-1.3B · Human T2V benchmarkHuman Anatomy: 78.1 -> 79.6Improved
Train jointly with motion instead of video-only fine-tuning on HuMoVe (ablation)Wan-5B · Human T2V benchmarkHuman Anatomy: 83.1 -> 85.1Improved
Video-only fine-tuning on HuMoVe (ablation)Wan-5B · Human T2V benchmarkHuman Anatomy: 83.0 -> 83.1No clear effect
Video-only fine-tuning on HuMoVe (ablation)Wan-1.3B · Human T2V benchmarkHuman Anatomy: 78.1 -> 77.4No clear effect
Add joint motion modelingWan-5B · Human T2V benchmarkAesthetic Quality: 58.3 -> 58.3No clear effect
Add MVS-RoPE (synchronized RoPE) (ablation)EchoMotion · attention-map analysistemporal alignmentImproved
EchoMotion vs closed-source models on complex motionVeo 3.1 / Kling 2.5 Turbo · Commercial comparisonVideo Quality (human): 90.2 / 90.4 vs 80.4Hurt
Use generative EchoMotion for video-to-motion instead of reconstruction modelHMR2.0 · 3DPWPA-MPJPE: 58.4 -> 59.8Hurt
EchoMotion vs earlier generative ChatPoseChatPose · 3DPWPA-MPJPE: 81.9 -> 59.8Improved
EchoMotion vs MotionGPT on motion generationMotionGPT · Motion generation (50 prompts)Prompt Following (human): 72.3 -> 82.3Improved

Later papers that compared with this method

1 later accepted paper reports EchoMotion 5B as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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