AI Paper Atlas

Research map / Image generation / Editing and style transfer

UniCoRN: A Unified Conditional Image Repainting Network

Jimeng Sun, Shuchen Weng, Zheng Chang, Si Li, Boxin Shi

CVPR 2022 · Image generation › Editing and style transfer · approach: Localized and attribute-specific editing · 5 citations (OpenAlex)

Check 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 UniCoRN instead of the strongest baselinePERSON-CIR · PERSON-CIRFID: 13.74 -> 11.45Improved
use UniCoRN instead of the strongest baselinePERSON-CIR · PERSON-CIRR-precision (%): 96.11 -> 97.42Improved
use UniCoRN instead of the strongest baselinePERSON-CIR · PERSON-CIRM-score: 3.86 -> 3.56Improved
use UniCoRN instead of the strongest baselineLANDSCAPE-CIR · LANDSCAPE-CIR (256 × 256)FID: 14.71 -> 9.96Improved
use UniCoRN instead of the strongest baselineLANDSCAPE-CIR · LANDSCAPE-CIR (256 × 256)R-precision (%): 96.73 -> 97.74Improved
use UniCoRN instead of the strongest baselineLANDSCAPE-CIR · LANDSCAPE-CIR (256 × 256)M-score: 3.18 -> 3.14Improved
use UniCoRN instead of the strongest baselineLANDSCAPE-CIR · LANDSCAPE-CIR (512 × 512)FID: 21.47 -> 18.63Improved
use UniCoRN instead of the strongest baselineLANDSCAPE-CIR · LANDSCAPE-CIR (512 × 512)R-precision (%): 96.96 -> 97.33Improved
use UniCoRN instead of the strongest baselineLANDSCAPE-CIR · LANDSCAPE-CIR (512 × 512)M-score: 15.66 -> 14.42Improved
use hierarchical HCMSM instead of CMSM (ablation)UniCoRN · PERSON-CIRFID: 15.03 -> 11.45Improved
use multiple encoder layers rather than a single layer in HCMSM (ablation)UniCoRN · PERSON-CIRFID: 12.40 -> 11.45Improved
connect the label-encoder units hierarchically (ablation)UniCoRN · PERSON-CIRFID: 12.21 -> 11.45Improved

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