AI Paper Atlas

Research map / Image generation / Image restoration

Trans-Adapter: A Plug-and-Play Framework for Transparent Image Inpainting

Yuekun Dai, Haitian Li, Shangchen Zhou, Chen Change Loy

ICCV 2025 · Image generation › Image restoration · approach: Image harmonization and color transformation · 2 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 spatial alignment module (ablation)Trans-Adapter (SD1.5-inpaint) · LayerBench blended noiseAS: 5.685 -> 6.097Improved
add spatial alignment module (ablation)Trans-Adapter (SD1.5-inpaint) · LayerBench blended noiseAEQ: 0.9897 -> 0.9878Hurt
add cross-domain self-attention (ablation)Trans-Adapter (SD1.5-inpaint) · LayerBench blended noiseAS: 6.065 -> 6.097Improved
use designed modules instead of original AnimateDiff (ablation)Trans-Adapter (SD1.5-inpaint) · LayerBench blended noiseLPIPS: 0.0459 -> 0.0408Improved
add MAGICK training data (ablation)Trans-Adapter (SD1.5-inpaint) · LayerBench blended noiseLPIPS: 0.0435 -> 0.0408Improved
add own 35K PNG-stock dataset (ablation)Trans-Adapter (SD1.5-inpaint) · LayerBench blended noiseLPIPS: 0.0457 -> 0.0408Improved
use LayerDiffuse RGB padding instead of grey background (ablation)Trans-Adapter (SD1.5-inpaint) · LayerBench blended noiseAEQ: 0.9717 -> 0.9878Improved
use LayerDiffuse RGB padding instead of Telea padding (ablation)Trans-Adapter (SD1.5-inpaint) · LayerBench blended noiseAEQ: 0.9853 -> 0.9878Improved
add alpha-map LoRA stage (ablation)Trans-Adapter (SD1.5-inpaint) · LayerBench pure noiseLPIPS: 0.0769 -> 0.0591Improved
unfreeze LoRA in stage 2 (ablation)Trans-Adapter (SD1.5-inpaint) · LayerBench blended noiseAEQ: 0.9831 -> 0.9878Improved
train LoRA on both RGB and alpha instead of alpha only (ablation)Trans-Adapter (SD1.5-inpaint) · LayerBench blended noiseAEQ: 0.9863 -> 0.9878Improved
joint RGBA inpainting instead of inpaint then BiRefNet mattingSD1.5-inpaint · LayerBench blended noiseLPIPS: 0.0515 -> 0.0408Improved

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