AI Paper Atlas

Research map / Image generation / Editing and style transfer

Rectifying Latent Space for Generative Single-Image Reflection Removal

Mingjia Li, Jin Hu, Hainuo Wang, Qiming Hu, Jiarui Wang, Xiaojie Guo

CVPR 2026 · Image generation › Editing and style transfer · approach: Inversion-based diffusion editing · 3 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
train the VAE with the reflection-equivariance loss in addition to reconstruction loss (ablation)GenSIRR (FLUX-based) · Real20PSNR: 25.79 -> 27.27Improved
add equivariance loss to VAE training (ablation)GenSIRR re-VAE · Real20SSIM (SIRR): 0.842 -> 0.871Improved
finetune VAE with reconstruction loss only versus FLUX VAE (ablation)VAE · Real20SSIM (SIRR): 0.841 -> 0.842No clear effect
add equivariance loss to VAE reconstruction (ablation)VAE · synthetic reconstruction (non-mixed)SSIM: 0.918 -> 0.919No clear effect
use learnable task-specific text embedding instead of fixed text prompt (ablation)GenSIRR · Real20PSNR: 26.52 -> 27.27Improved
use learnable embedding instead of fixed prompt (ablation)GenSIRR · Real20SSIM: 0.830 -> 0.871Improved
initialize prompt randomly or with RDNet prompt generator instead of fixed-text initialization (ablation)GenSIRR · Real20convergenceHurt
add DEBS with k=4 (ablation)GenSIRR · Real20PSNR: 27.27 -> 27.58Improved
increase DEBS candidates from 4 to 16 (ablation)GenSIRR · Real20PSNR: 27.58 -> 27.74Improved
increase DEBS candidates from 4 to 16 (ablation)GenSIRR · Real20SSIM: 0.881 -> 0.882No clear effect
increase DEBS candidates from 1 to 16 (ablation)GenSIRR · Inference cost (256x256)inference time (ms): 2061.9 -> 3952.4Hurt
use GenSIRR instead of DAI and RDNetreflection removal · OpenRR-val (human evaluation)average success rate (%): 41.2% -> 96.6%Improved

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