AI Paper Atlas

Research map / Image generation / Editing and style transfer

A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting

Junhao Zhuang, Yanhong Zeng, WENRAN LIU, Chun Yuan, Kai Chen

ECCV 2024 · Image generation › Editing and style transfer · approach: Localized and attribute-specific editing · 146 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
use learnable task prompts instead of unlearnable rare identifiers (ablation)PowerPaint · Places2 context inpaintingFID: 3.11 -> 2.59Improved
use learnable task prompts instead of unlearnable rare identifiers (ablation)PowerPaint · MSCOCO object inpainting (bbox)Local-FID: 13.03 -> 11.61Improved
train one unified model with task prompts instead of separate task-specific models (ablation)PowerPaint · Flickr-Scenery outpaintingFID: 10.24 -> 10.16Improved
unified model vs task-specific on text-guided object inpainting (ablation)PowerPaint · OpenImages bbox object inpaintingCLIP Score: 27.58 -> 27.56No clear effect
fine-tune SD-Inpainting on the same fine-tuning data as PowerPaint (ablation)SD-Inpainting · OpenImages bbox object inpaintingLocal-FID: 12.71 -> 12.83No clear effect
use object-removal prompt as positive and object-insertion prompt as negative prompt with classifier-free guidancePowerPaint · context-aware inpainting and object removalartifact generation: Places2 FID 2.82 -> 2.59 vs SD-Inpainting with default promptImproved
use PowerPaint instead of SmartBrush for context-aware inpainting and outpaintingSmartBrush · Flickr-Scenery outpaintingFID: 105.99 -> 10.16Improved
use PowerPaint instead of LaMa for context-aware inpaintingLaMa · Places2 context-aware inpainting (all samples)LPIPS: 0.1193 -> 0.1263Hurt
use PowerPaint instead of SmartBrush for text-guided object inpaintingSmartBrush · OpenImages bbox object inpaintingCLIP Score: 27.61 -> 27.56No clear effect

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