AI Paper Atlas

Research map / Video / Video generation

Pose Guided Human Video Generation

Ceyuan Yang, Zhe Wang, Xinge Zhu, Chen Huang, Jianping Shi, Dahua Lin

ECCV 2018 · Video › Video generation · approach: Trajectory-guided motion control · 142 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 adversarial loss instead of L1-only training (ablation)PSGAN · Human Action Dataset (UCF101 + Weizmann)average pairwise L2 distance (lower is better): 0.0124 -> 0.0064Improved
add adversarial loss instead of L1-only training (ablation)PSGAN · Human Facial Dataset (CK+)average pairwise L2 distance (lower is better): 0.0078 -> 0.0051Improved
add LSTM/GRU temporal module (ablation)PSGAN · Human Action Dataset (UCF101 + Weizmann)average pairwise L2 distance (lower is better): 0.0072 -> 0.0064Improved
add LSTM/GRU temporal module (ablation)PSGAN · Human Facial Dataset (CK+)average pairwise L2 distance (lower is better): 0.0062 -> 0.0051Improved
add adversarial loss instead of L1-only training (ablation)PSGAN · Human Action Dataset (UCF101 + Weizmann) user studyfraction ranking 1st: 0.09 -> 0.32Improved
add LSTM/GRU temporal module (ablation)PSGAN · Human Action Dataset (UCF101 + Weizmann) user studyfraction ranking 1st: 0.21 -> 0.32Improved
add predicted-pose stream with semantic consistency to ground-truth-pose training (SCGAN vs SCGAN-gen) (ablation)SCGAN · Human Action Dataset (UCF101 + Weizmann)SSIM (higher is better): 0.73 -> 0.87Improved
add predicted-pose stream with semantic consistency to ground-truth-pose training (SCGAN vs SCGAN-gen) (ablation)SCGAN · Human Action Dataset (UCF101 + Weizmann)LPIPS (lower is better): 0.083 -> 0.041Improved
add predicted-pose stream with semantic consistency to ground-truth-pose training (SCGAN vs SCGAN-gen) (ablation)SCGAN · Human Facial Dataset (CK+)SSIM (higher is better): 0.89 -> 0.91Improved
add predicted-pose stream with semantic consistency to ground-truth-pose training (SCGAN vs SCGAN-gen) (ablation)SCGAN · Human Facial Dataset (CK+)LPIPS (lower is better): 0.038 -> 0.026Improved
train on predicted plus ground-truth poses (SCGAN) vs ground-truth only (SCGAN-gt) (ablation)SCGAN · Human Action Dataset (UCF101 + Weizmann)SSIM (higher is better): 0.89 -> 0.87No clear effect
use pose-guided PSGAN+SCGAN instead of MoCoGANOurs · Human Action Dataset (UCF101 + Weizmann)Inception Score: 4.02 -> 5.70Improved

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