AI Paper Atlas

Research map / Image generation / Editing and style transfer

Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment

Taewoo Kim, Chaeyeon Chung, Yoonseo Kim, Sunghyun Park, Kangyeol Kim, Jaegul Choo

ECCV 2022 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 30 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 target hair alignment step (ablation)Style Your Hair · FFHQ hairstyle transferFID: 43.37 -> 39.68Improved
add semantic label of occluded regions to source segmentation (ablation)Style Your Hair · FFHQ hairstyle transferFID: 39.68 -> 32.69Improved
add independent source inpainting optimization step (ablation)Style Your Hair · FFHQ hairstyle transferFID: 32.69 -> 18.02Improved
add local-style-matching loss (ablation)Style Your Hair · VoxCeleb2 reconstructionLPIPS: 0.2082 -> 0.2078Improved
add local-style-matching loss (ablation)Style Your Hair · VoxCeleb2 reconstructionSSIM: 0.7716 -> 0.7717No clear effect
add regularization loss L_reg (ablation)Style Your Hair · VoxCeleb2 reconstructionSSIM: 0.7667 -> 0.7716Improved
add regularization loss L_reg (ablation)Style Your Hair · VoxCeleb2 reconstructionLPIPS: 0.2125 -> 0.2082Improved
Ours vs Barbershop at large pose differenceStyle Your Hair · FFHQ Difficult pose differenceFID: 26.30 -> 22.72Improved
Ours vs Barbershop at small pose differenceStyle Your Hair · FFHQ Easy pose differenceFID: 20.75 -> 20.79No clear effect
Ours vs HairFIT on K-hairstyle reconstructionStyle Your Hair · K-hairstyleLPIPS: 0.2054 -> 0.1786Improved
Ours vs HairFIT on VoxCeleb2 reconstructionStyle Your Hair · VoxCeleb2LPIPS: 0.2033 -> 0.2078Hurt

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