AI Paper Atlas

Research map / Image generation / GANs

SSCL: Adversarially Guided Image Compression via Semantic and Spectral Consistency Learning

Wei Jiang, Yongqi Zhai, Jiayu Yang, Bohao Feng, Wenqiang Wang, Bo Huang, Lin Ding, Ronggang Wang

AAAI 2026 · Image generation › GANs · approach: GAN-based image manipulation · 1 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 semantic and spectral discriminators to patch-wise adversarial training (ablation)SSCL on MLIC++ · CLIC 2020FID BD-rate (%): 0 -> -28.5Improved
add semantic and spectral discriminators to patch-wise adversarial training (ablation)SSCL on MLIC++ · CLIC 2020DISTS BD-rate (%): 0 -> -21.6Improved
add semantic and spectral discriminators (distortion cost) (ablation)SSCL on MLIC++ · CLIC 2020PSNR BD-rate (%): 0 -> 0.7Hurt
add one of the two extra discriminators to patch-wise training (partial variant) (ablation)SSCL on MLIC++ · CLIC 2020FID BD-rate (%): 0 -> -17.9Improved
use SSCL discriminators instead of MS-ILLM trainingperceptual codec · CLIC 2020FID BD-rate vs MS-ILLM (%): 0.0 -> -35.9Improved
use SSCL instead of MS-ILLMperceptual codec · KodakDISTS BD-rate vs MS-ILLM (%): 0.0 -> -59.6Improved
use SSCL instead of distortion-oriented MLIC++codec · CLIC 2020PSNR BD-rate vs MS-ILLM (%): -59.2 -> -13.4Hurt
use SSCL one-step decoder instead of diffusion decodersperceptual codec · CLIC 2020decoding time (s): 60.03 -> 0.33Improved
add SSCL discriminators (training only)MLIC++ backbone · model complexityparameters (M), VRAM: 83.5 (same as MLIC++)No clear effect
add semantic and spectral discriminators on training stabilitySSCL · trainingadversarial loss: stable around 0.693No 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