AI Paper Atlas

Research map / Image generation / GANs

Edge Guided GANs With Multi-Scale Contrastive Learning for Semantic Image Synthesis

Hao Tang, Guolei Sun, Nicu Sebe, Luc Van Gool

TPAMI 2023 · Image generation › GANs · approach: Conditional GANs · 23 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 edge generator G_e (ablation)E+G_i baseline · CityscapesmIoU: 58.6 -> 60.2Improved
add edge generator G_e (ablation)E+G_i baseline · ADE20KmIoU: 36.9 -> 38.7Improved
add edge generator G_e (ablation)E+G_i baseline · COCO-StuffmIoU: 36.8 -> 37.5Improved
add attention guided edge transfer G_t (ablation)E+G_i+G_e · ADE20KmIoU: 38.7 -> 40.6Improved
add semantic preserving module G_s (ablation)E+G_i+G_e+G_t · CityscapesmIoU: 61.5 -> 64.5Improved
add G_l component (ablation)B4 model · ADE20KmIoU: 42.0 -> 45.8Improved
add G_c component (class-specific generation) (ablation)B5 model · CityscapesFID: 52.2 -> 44.5Improved
add G_c component (ablation)B5 model · ADE20KmIoU: 45.8 -> 50.6Improved
add first multi-scale contrastive loss term (ablation)ECGAN (B6) · ADE20KmIoU: 50.6 -> 51.6Improved
add second cross-scale loss term (ECGAN++) (ablation)B7 · ADE20KmIoU: 51.6 -> 52.7Improved
full ECGAN++ over ECGANECGAN · COCO-StuffFID: 15.7 -> 14.9Improved
ECGAN++ vs OASIS on small objectsOASIS · Cityscapes small objectsmIoU: 26.0 -> 29.4Improved

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