AI Paper Atlas

Research map / Image generation / GANs

Ph-GAN: Physics-Inspired GAN for Generating SAR Images Under Limited Data

Xidan Zhang, Yihan Zhuang, Qian Guo, Haodong Yang, Xuelin Qian, Gong Cheng, Junwei Han, Zhongling Huang

ICCV 2025 · Image generation › GANs · approach: GAN latent optimization and evaluation

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 physics-inspired regularization (PSC losses)ACGAN · 10% MSTARFID: 290.0484 -> 87.2719Improved
add physics-inspired regularization (PSC losses)ACGAN · 5% MSTARFID: 340.2440 -> 130.2311Improved
add physics-inspired regularizationStyleGAN · 10% MSTARFID: 290.6406 -> 174.8329Improved
add physics-inspired regularizationStyleGAN · 1% OpenSARShipFID: 45.0999 -> 44.7829No clear effect
add physics-inspired regularizationCVAE-GAN · 1% OpenSARShipFID: 23.9480 -> 15.0530Improved
add DiffAugment (DA) to ACGANACGAN · 10% MSTARFID: 290.0484 -> 1089.4734Hurt
add ADA to ACGANACGAN · 10% MSTARFID: 290.0484 -> 320.5937Hurt
add DIG to ACGANACGAN · 5% MSTARFID: 340.2440 -> 438.7845Hurt
add image-level generator physical loss (ablation)ACGAN · 10% MSTARFID: 290.0484 -> 97.4472Improved
add discriminator physical loss alone (ablation)ACGAN · 10% MSTARFID: 290.0484 -> 92.7562Improved
add discriminator loss to generator physical losses (ablation)ACGAN · 10% MSTARFID: 177.1856 -> 87.2719Improved
add image-level generator loss to feature-level generator and discriminator losses (ablation)ACGAN · 10% MSTARFID: 95.9290 -> 87.2719Improved

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