AI Paper Atlas

Research map / Video / Video generation

DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation

Donglin Di, He Feng, Wenzhang Sun, Yongjia Ma, Hao Li, Wei Chen, Lei Fan, Tonghua Su, Xun Yang

ICCV 2025 · Video › Video generation · approach: Compositional text-to-video diffusion · 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
train on DH-FaceVid-1K instead of CelebV-Text (ablation)CogVideoX · Text-to-VideoFVD: 129.59 -> 98.01Improved
train on DH-FaceVid-1K instead of CelebV-Text (ablation)AnimateDiff · Text-to-VideoFVD: 174.59 -> 156.13Improved
train on DH-FaceVid-1K instead of CelebV-Text (ablation)CogVideoX · Image-to-VideoFVD: 123.25 -> 92.31Improved
train on DH-FaceVid-1K instead of CelebV-Text (ablation)SVD · Image-to-VideoFVD: 162.59 -> 132.92Improved
train on DH-FaceVid-1K instead of CelebV-Text (ablation)EasyAnimate · Text-to-VideoCLIP: 0.9274 -> 0.9240Hurt
train on DH-FaceVid-1K instead of CelebV-Text (ablation)I2VGen-XL · Image-to-VideoCLIP: 0.9067 -> 0.9013Hurt
train on DH-FaceVid-1K instead of CelebV-Text (ablation)CogVideoX · Text-to-VideoCLIP: 0.9388 -> 0.9401Improved
increase training data from 100h to 1000h (ablation)CogVideoX-5B · Text-to-VideoFVD: 237.52 -> 98.01Improved
increase training data from 600h to 1000h (ablation)CogVideoX-2B · Text-to-VideoFVD: 145.14 -> 150.27Hurt
increase training data from 100h to 600h (ablation)CogVideoX-2B · Text-to-VideoFVD: 215.06 -> 145.14Improved
increase training data from 600h to 1000h (ablation)CogVideoX-2B · Image-to-VideoFVD: 135.14 -> 141.36Hurt
increase model size from 2B to 5B at 1000h (ablation)CogVideoX · Image-to-VideoFVD: 141.36 -> 92.31Improved

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