AI Paper Atlas

Research map / Image generation / Editing and style transfer

EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal

Sanghyun Jo, Donghwan Lee, Eunji Jung, Seong Je Oh, Kyungsu Kim

ECCV 2026 · Image generation › Editing and style transfer · approach: Localized and attribute-specific editing · 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 EraseLoRA (BFE + BRSA)SD3.5-M · OpenImages V7 (200 samples)BG Sim.: 0.605 to 0.743Improved
add EraseLoRA (BFE + BRSA)SD3.5-M · RORD (343 frames)BG Sim.: 0.582 to 0.779Improved
add EraseLoRA (BFE + BRSA)SD3.5-M · OpenImages V7 (200 samples)FG Sim.: 0.286->0.151Improved
add EraseLoRA (BFE + BRSA)SD3.5-M · RORD (343 frames)FG Sim.: 0.319->0.138Improved
add EraseLoRASD3.5-M · OpenImages V7 (200 samples)BG Pres.: 0.934 to 0.924No clear effect
add BFE to AttentiveEraser (ablation)AttentiveEraser · OpenImages V7 (200 samples)BG Sim.: 0.559 to 0.596Improved
add BFE to AttentiveEraser (ablation)AttentiveEraser · OpenImages V7 (200 samples)FG Sim.: 0.276 to 0.252Improved
add BFE to DesignEdit (ablation)DesignEdit · OpenImages V7 (200 samples)BG Sim.: 0.600 to 0.603Improved
add background puzzle loss to reconstruction loss (ablation)EraseLoRA · OpenImages V7 (200 samples)BG Sim.: 0.736 to 0.743Improved
add background puzzle loss to reconstruction loss (ablation)EraseLoRA · OpenImages V7 (200 samples)FG Sim.: 0.158 to 0.151Improved
add reconstruction loss to puzzle loss (ablation)EraseLoRA · OpenImages V7 (200 samples)BG Sim.: 0.561 to 0.743Improved
use InternVL3-78B instead of LLaVA-7B as MLLM (ablation)EraseLoRA · OpenImages V7 (200 samples)BG Sim.: 0.728 to 0.743Mixed

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