AI Paper Atlas

Research map / Image generation / Editing and style transfer

EraseDraw : Learning to Insert Objects by Erasing Them from Images

Alper Canberk, Maksym Bondarenko, Ege Ozguroglu, Ruoshi Liu, Carl Vondrick

ECCV 2024 · Image generation › Editing and style transfer · approach: Localized and attribute-specific editing · 4 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
learn insertion from erased-object data instead of InstructPix2Pix training dataEraseDraw · EmuEdit add-instruction validationCLIPdir: 0.0976 -> 0.1383Improved
use EraseDraw instead of MagicBrush++ for insertionEmuEdit add-instruction validation · EmuEdit add-instruction validationhuman win rate (%): 55.06 -> 82.22Improved
mix autonomously generated EraseDraw-15k with GQA-Insert for training (ablation)EraseDraw · EmuEdit add-instruction validationCLIPdir: 0.12788 -> 0.1383Improved
train on 15,000 autonomously generated images instead of 50,000 GQA-derived images (ablation)EraseDraw · EmuEdit add-instruction validationCLIPout: 0.0907 -> 0.0905No clear effect
insert objects iteratively step by step instead of one-shot prompting with Stable Diffusion 1.5EraseDraw · iterative scene composition (qualitative)prompt adherenceImproved
add CLIP-score beam search to select candidates across insertion stepsEraseDraw iterative generation · iterative scene composition (qualitative)prompt adherenceImproved

Later papers that compared with this method

1 later accepted paper reports EraseDraw as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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