AI Paper Atlas

Research map / Image generation / Editing and style transfer

H-Adapter: Pose-Robust Hairstyle Transfer via Attention-Derived, Source-Aligned Hair Masks

Seulgi Jeong, Yunseong Cho, Sanghun Park

ECCV 2026 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 0 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 region-specific loss (H-Adapter instead of IP-Adapter, t8 mask) (ablation)H-Adapter · CelebA-HQ pose-different subsetFID: 15.27 -> 12.47Improved
add region-specific loss (vs IP-Adapter t8) (ablation)H-Adapter · CelebA-HQ pose-different subsetFID_CLIP: 8.83 -> 3.98Improved
add region-specific loss (vs IP-Adapter t8) (ablation)H-Adapter · CelebA-HQ pose-different subsetCLIP-I: 0.639 -> 0.659Improved
add region-specific loss (vs IP-Adapter t8) (ablation)H-Adapter · CelebA-HQ pose-different subsetSSIM: 0.803 -> 0.831Improved
add region-specific loss (vs IP-Adapter t8) (ablation)H-Adapter · CelebA-HQ pose-different subsetPSNR: 21.56 -> 23.06Improved
add region-specific loss (vs IP-Adapter with t2 mask) (ablation)H-Adapter · CelebA-HQ pose-different subsetFID_CLIP: 4.26 -> 3.98Improved
add region-specific loss (vs IP-Adapter with t2 mask) (ablation)H-Adapter · CelebA-HQ pose-different subsetCLIP-I: 0.651 -> 0.659Improved
H-Adapter vs HairFastGANH-Adapter · CelebA-HQ pose-different subsetPSNR: 24.40 -> 23.06Hurt
H-Adapter vs HairFastGANH-Adapter · CelebA-HQ pose-different subsetFID: 12.78 -> 12.47Improved
H-Adapter vs Stable-HairH-Adapter · VLM-as-a-judge GPT-4oHFS: 2.90 -> 3.11Improved
H-Adapter vs HairCLIPv2H-Adapter · VLM-as-a-judge GPT-4oHFS: 2.10 -> 3.11Improved
H-Adapter vs Style-Your-Hair on artifact qualityH-Adapter · VLM-as-a-judge GPT-4oAQS: 3.61 -> 3.73No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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