AI Paper Atlas

Research map / 3D vision / Human pose estimation

Liquid Warping GAN With Attention: A Unified Framework for Human Image Synthesis

Wen Liu, Zhixin Piao, Zhi Tu, Wenhan Luo, Lin Ma, Shenghua Gao

TPAMI 2021 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 49 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 personalization (one/few-shot finetuning) (ablation)AttLWB · Youtube-Dancer-18PSNR: 16.932 -> 17.974Improved
add personalization (one/few-shot finetuning) (ablation)AttLWB · Youtube-Dancer-18FID: 79.321 -> 59.832Improved
replace LWB with attentional AttLWB (ablation)LWB · Novel view synthesis (MotionSynthetic)PSNR: 25.055 -> 28.625Improved
replace LWB with attentional AttLWB (ablation)LWB · One-shot motion imitation self-imitationFace-CS: 0.560 -> 0.591Improved
replace LWB with attentional AttLWB (ablation)LWB · Appearance transfer (iPER)SSIM: 0.734 -> 0.726Hurt
add adversarial loss to perceptual loss (ablation)AttLWB · Youtube-Dancer-18PSNR: 18.204 -> 19.656Improved
add face identity loss to perceptual + adversarial (ablation)AttLWB · Youtube-Dancer-18PSNR: 19.656 -> 19.542Mixed
add attention regularization loss to complete the full loss (ablation)AttLWB · Youtube-Dancer-18PSNR: 19.542 -> 20.038Improved
increase number of source images s_n with small steps T=10 (ablation)AttLWB · Youtube-Dancer-18PSNR: s_n=8, T=10 decreasesHurt
increase number of source images s_n with large T (ablation)AttLWB · Youtube-Dancer-18PSNRImproved
increase personalization steps T beyond about 150 (ablation)AttLWB · Youtube-Dancer-18PSNR: saturates at around 150 stepsNo clear effect
use attention aggregation (AttLWB) over other warping strategies (ablation)AttLWB · User study (64 volunteers)user preference %: 41.73% vs 20.04%Improved

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