AI Paper Atlas

Research map / Image generation / Editing and style transfer

ReFocusEraser: Refocusing for Small Object Removal with Robust Context-Shadow Repair

Qingping Zheng, Bo Huang, Yang Liu, Haoyu Zhao, Ling Zheng, Zengmao Wang, Ying Li, Jiankang Deng

ICLR 2026 · Image generation › Editing and style transfer · approach: Localized and attribute-specific editing

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 Camera-Adaptive Refocus (3x zoom, box stitching) to LoRA baseline (ablation)FLUX.1-dev LoRA inpainter · RORD-val (small objects)PSNR: 23.683 -> 31.082Improved
increase training focal length from 1x to 2x (ablation)Stage-I inpainter · RORD-val (small objects)FID: 40.287 -> 19.597Improved
increase training focal length from 1x to 3x (ablation)Stage-I inpainter · RORD-val (small objects)PSNR: 23.683 -> 29.574Improved
increase training focal length from 1x to 3x (ablation)Stage-I inpainter · RORD-val (small objects)FID: 40.287 -> 13.283Improved
use mask-based instead of box-based stitching at 2x (ablation)Stage-I inpainter · RORD-val (small objects)PSNR: 31.245 -> 31.905Improved
use mask-based instead of box-based stitching at 2x (ablation)Stage-I inpainter · RORD-val (small objects)FID: 8.458 -> 13.041Hurt
use mask-based instead of box-based stitching at 3x (ablation)Stage-I inpainter · RORD-val (small objects)PSNR: 31.082 -> 31.732Improved
use mask-based instead of box-based stitching at 3x (ablation)Stage-I inpainter · RORD-val (small objects)FID: 24.288 -> 25.036Hurt
add seam- and shadow-aware decoder repair on top of mask stitching (ablation)ReFocusEraser · RORD-val (small objects)FID: 25.036 -> 21.378Improved
replace L1 decoder loss with LPIPS (ablation)Stage-II decoder · RORD-val (small objects)FID: 24.580 -> 24.618No clear effect
L1 on background with LPIPS on foreground instead of L1 only (ablation)Stage-II decoder · RORD-val (small objects)FID: 24.580 -> 24.124No clear effect
LPIPS on background plus L1 on foreground instead of L1 only (ablation)Stage-II decoder · RORD-val (small objects)FID: 24.580 -> 21.379Improved

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