AI Paper Atlas

Research map / Image generation / Editing and style transfer

Supervised Attribute Information Removal and Reconstruction for Image Manipulation

Nannan Li, Bryan A. Plummer

ECCV 2022 · 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
add disentanglement loss (attribute remover) (ablation)AIRR · CelebA-HQAvg. manipulation accuracy: 64.5 -> 73.7Improved
add disentanglement loss (attribute remover) (ablation)AIRR · DeepFashion Fine-grained AttributeAvg. manipulation accuracy: 60.8 -> 62.1Improved
add disentanglement loss (attribute remover) (ablation)AIRR · DeepFashion SynthesisAvg. manipulation accuracy: 91.7 -> 95.3Improved
add disentanglement loss (attribute remover) (ablation)AIRR · CelebAAvg. manipulation accuracy: 81.8 -> 86.2Improved
add parsing mask and background encoder branch (ablation)AIRR · DeepFashion Fine-grained AttributeAvg. manipulation accuracy: 45.4 -> 62.1Improved
add parsing mask and background encoder branch (ablation)AIRR · DeepFashion SynthesisR@5: 94.4 -> 97.6Improved
add parsing mask and background encoder branch (ablation)AIRR · CelebAAvg. manipulation accuracy: 83.0 -> 86.2Improved
use disentanglement loss instead of honesty loss (ablation)AIRR · DeepFashion Fine-grained AttributeR@5: 51.1 -> 57.7Improved
use disentanglement loss instead of honesty loss (ablation)AIRR · DeepFashion SynthesisAvg. manipulation accuracy: 90.0 -> 95.3Improved
AIRR vs AttGAN, strongest baselineAIRR · CelebAAvg. manipulation accuracy: 69.5 -> 86.2Improved
AIRR vs InterfaceGAN with ablated model (w/o mask)AIRR (w/o mask) · CelebA-HQR@5: 19.1 -> 60.9Improved
user study: AIRR vs StarGANAIRR · DeepFashion Fine-grained Attributeuser preference: 65%/35%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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