AI Paper Atlas

Research map / Image generation / Image restoration

Diff-SemiER: Transparency-Aware Adaptive Fusion Diffusion Model with Generative Prior for Semi-Transparent Eyeglasses Removal

Jiahao Li, Shiqi Yin, Zhenxiang Lian, Jingtao Guo

CVPR 2026 · Image generation › Image restoration · approach: Reflection removal

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 restoration branch (TAFDM) with generative prior instead of GPDM alone (ablation)Diff-SemiER · FFHQ-TestIDD: 0.682 -> 0.534Improved
add generative prior from GPDM to TAFDM (ablation)Diff-SemiER · FFHQ-TestPSNR: 35.79 -> 36.16Improved
add generative prior from GPDM to TAFDM (ablation)Diff-SemiER · FFHQ-TestIDD: 0.581 -> 0.534Improved
add SMAF adaptive fusion on top of soft mask only (ablation)Diff-SemiER · FFHQ-TestPSNR: 35.64 -> 36.16Improved
add transparency soft mask modulation in SMAF (ablation)Diff-SemiER · FFHQ-TestPSNR: 36.10 -> 36.16Improved
add transparency soft mask modulation in SMAF (ablation)Diff-SemiER · FFHQ-TestIDD: 0.543 -> 0.534Improved
use Diff-SemiER instead of RDDMsemi-transparent eyeglasses removal · FFHQ-TestPSNR: 35.33 -> 36.16Improved
use Diff-SemiER instead of RDDM on real-world CelebA-HQsemi-transparent eyeglasses removal · Real-world CelebA-HQFID: 99.53 -> 99.80No clear effect
use Diff-SemiER instead of RDDM on real-world FFHQsemi-transparent eyeglasses removal · Real-world FFHQFID: 66.21 -> 66.13No clear effect
use Diff-SemiER instead of RDDM in pairwise user studysemi-transparent eyeglasses removal · User study FFHQpreference (%): 31.72%/68.28%Improved

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