We prioritize simplicity and performance over functionality. As a minimal baseline, our model does only basic image generation, lacking many features required for downstream tasks. Think of it as DCGAN in 2025 rather than something feature-rich like StyleGAN. We hope this helps further GAN research!

Given the well-behaved loss, we move away from the 2015-ish architecture in StyleGAN and implement G and D with a minimalist yet modern architecture---a simplified ConvNeXt. With the two components combined, we obtain a simple GAN baseline that is stable to train and surpasses StyleGAN performance.

To further GAN research, we first improve the GAN loss to alleviate mode dropping and non-convergence. This makes GAN optimization sufficiently easy that we can now discard existing GAN tricks w/o training failure. The dependence on outdated GAN-specific architectures is also eliminated.

GANs are often criticized for their training instability, and it is often believed that GANs cannot work w/o many engineering tricks. They use outdated network architectures without modern backbone advances. These supposed weaknesses resulted in the abandonment of GAN research in favor of diffusion.

Can GANs compete in 2025? In 'The GAN is dead; long live the GAN! A Modern GAN Baseline', we show that a minimalist GAN w/o any tricks can match the performance of EDM with half the size and one-step generation - github.com/brownvc/r3gan - work of Nick Huang, @skylion.bsky.social, Volodymyr Kuleshov

But what if you _really_ like reflections? Local Gaussian Density Mixtures updates lumigraphs by optimizing mixtures of per-view volumes for 🌟maximum shine🌟 #SIGGRAPHAsia2024 xchaowu.github.io/papers/lgdm/... First author Xiuchao Wu is graduating soon and is looking for a job!