Papers › CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and...
CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction
Shengke Sun, Ziqian Luan, Zhanshan Zhao, Shijie Luo and Shuzhen Han
Generative Adversarial Networks(GANs) have received considerable attention due to its outstanding ability to generate images. However, training a GAN is hard since the game between the Generator(G) and the Discriminator(D) is unfair. Towards making the competition fairer, we propose a new perspective of training GANs, named Consistent Latent Representation and Reconstruction(CLR-GAN). In this paradigm, we treat the G and D as an inverse process, the discriminator has an additional task to restore the pre-defined latent code while the generator also needs to reconstruct the real input, thus obtaining a relationship between the latent space of G and the out-features of D. Based on this prior, we can put D and G on an equal position during training using a new criterion. Experimental results on various datasets and architectures prove our paradigm can make GANs more stable and generate better quality images(31.22% gain of FID on CIFAR10 and 39.5% on AFHQ-Cat, respectively). We hope that the proposed perspective can inspire researchers to explore different ways of viewing GANs training, rather than being limited to a two-player game. The code is publicly available at https://github.com/Petecheco/CLR-GAN.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Generation | AFHQ Cat | CLR-GAN | FID | 4.45 | #7 of 8 | Archive leaderboard | report |
| Image Generation | CIFAR-10 | CLR-GAN | FID | 23.3 | #59 of 78 | Archive leaderboard | report |
| Image Generation | CelebA 64x64 | CLR-GAN | FID | 13.63 | #29 of 39 | Archive leaderboard | report |
| Image Generation | FFHQ 256 x 256 | CLR-GAN | FID | 3.37 | #16 of 51 | Archive leaderboard | report |
| Image Generation | FFHQ 256 x 256 | CLR-GAN | Precision | 0.71 | #16 of 51 | Archive leaderboard | report |
| Image Generation | FFHQ 256 x 256 | CLR-GAN | Recall | 0.44 | #16 of 51 | Archive leaderboard | report |
| Image Generation | ImageNet 64x64 | CLR-GAN | FID | 20.27 | #29 of 65 | Archive leaderboard | report |
| Image Generation | LSUN Churches 256 x 256 | CLR-GAN | FID | 3.43 | #9 of 27 | Archive leaderboard | report |
| Image Generation | LSUN Churches 256 x 256 | CLR-GAN | Recall | 0.48 | #9 of 27 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections