AI Paper Atlas

Research map / Video / Video generation

Cross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video Reassembling

Subin Jeon, Seonghyeon Nam, Seoung Wug Oh, Seon Joo Kim

ECCV 2020 · Video › Video generation · approach: Diffusion-based human image animation · 8 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 cross-identity reconstruction training (ablation)pose-attentive reassembling network · VoxCeleb2 (cross-identity)FID: 55.11 -> 36.39Improved
add cross-identity reconstruction training (ablation)pose-attentive reassembling network · VoxCeleb2 (cross-identity)AED: 0.76 -> 0.62Improved
add cross-identity reconstruction training (ablation)pose-attentive reassembling network · VoxCeleb2 (self-reconstruction)AKD: 5.79 -> 1.90Improved
add cross-identity reconstruction training (ablation)pose-attentive reassembling network · VoxCeleb2 (self-reconstruction)FID: 18.49 -> 17.24Improved
add cross-identity reconstruction training (ablation)pose-attentive reassembling network · VoxCeleb2 (self-reconstruction)AED: 0.39 -> 0.38No clear effect
use pose-attentive retrieval instead of ConcatAppearance (ablation)pose-attentive reassembling network · VoxCeleb2 (cross-identity)FID: 63.52 -> 36.39Improved
use pose-attentive retrieval instead of ConcatAppearance (ablation)pose-attentive reassembling network · VoxCeleb2 (self-reconstruction)AKD: 4.21 -> 1.90Improved
use pose-attentive retrieval instead of ConcatNearest (ablation)pose-attentive reassembling network · VoxCeleb2 (cross-identity)FID: 52.13 -> 36.39Improved
use pose-attentive retrieval instead of ConcatAverage (ablation)pose-attentive reassembling network · VoxCeleb2 (self-reconstruction)AKD: 103.78 -> 1.90Improved
increase source frames from 1 to 32pose-attentive reassembling network · VoxCeleb2 few-shotAED: 0.46 -> 0.29Improved
increase source frames from 1 to 32pose-attentive reassembling network · VoxCeleb2 few-shotAKD: 7.47 -> 4.09Improved
increase source frames from 1 to 32pose-attentive reassembling network · VoxCeleb2 few-shotFID: 56.19 -> 60.80Hurt

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