AI Paper Atlas

Research map / Video / Video generation

OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation

Lei Zhu, xing cai, Yingjie Chen, Li YiHeng, Binxin Yang, Hao Liu, Jie Chen, Chen Li, Jing LYU

ECCV 2026 · Video › Video generation · approach: Trajectory-guided motion control · 3 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
fine-tune on 20% of OmniHuman dataLTX-2 · OHBench I2AVKL divergence (audio): 1.04 -> 0.77Improved
fine-tune on OmniHuman subsetLTX-2 · OHBench I2AVAbS: 3.69 -> 4.13Improved
fine-tune on OmniHuman subsetLTX-2 · OHBench I2AVT-A: 0.28 -> 0.35Improved
fine-tune on OmniHuman subsetLTX-2 · OHBench I2AVDD: 0.601 -> 0.665Improved
fine-tune on OmniHuman subsetLTX-2 · OHBench I2AVIC* dual-person ID consistency: 0.562 -> 0.589Improved
fine-tune on OmniHuman subsetLTX-2 · OHBench I2AVCN contact naturalness: 6.98 -> 7.32Improved
fine-tune on OmniHuman subsetLTX-2 · OHBench I2AVIQ: 0.720 -> 0.721No clear effect
fine-tune on OmniHuman subsetLTX-2 · OHBench I2AVLR listener realism: 8.94 -> 8.92No clear effect
fine-tune on OmniHuman subsetLTX-2 · OHBench I2AVWER: 0.29 -> 0.27Improved

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