AI Paper Atlas

Research map / Image generation / Editing and style transfer

WaveIPT: Joint Attention and Flow Alignment in the Wavelet domain for Pose Transfer

Liyuan Ma, Tingwei Gao, Haitian Jiang, Haibin Shen, Kejie Huang

ICCV 2023 · Image generation › Editing and style transfer · approach: Image-to-image translation · 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
fuse attention and flow in the wavelet domain instead of spatial mask fusion (ablation)WaveIPT · DeepFashion 256x176FID: 9.1026 -> 9.0264Improved
add Intra-scale Local Correlation (ILC) in place of mask-based wavelet fusion (ablation)WaveIPT · DeepFashion 256x176FID: 9.0264 -> 8.8861Improved
add Inter-scale Feature Interaction (IFI) on top of ILC (ablation)WaveIPT · DeepFashion 256x176FID: 8.8861 -> 8.9797 (LPIPS VGG 0.2356 -> 0.2347)Mixed
add Progressive Flow Regularization (PFR) on top of ILC+IFI (ablation)WaveIPT · DeepFashion 256x176FID: 8.9797 -> 8.8259Improved
use WaveIPT at higher resolution versus FreqHPTWaveIPT · DeepFashion 512x352FID: 6.5522 -> 4.8201Improved
use WaveIPT at higher resolution versus FreqHPTWaveIPT · DeepFashion 512x352SSIM: 0.7456 -> 0.7416Hurt

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