fid scores
FID (Fréchet Inception Distance) scores are a metric used to evaluate the quality of generated images by measuring the distance between feature distributions of generated images and real images in a pre-trained Inception network.
- Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling
- Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking
- Bilevel Optimization for Adversarial Learning Problems: Sharpness, Generation, and Beyond
- CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis
- GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation
- Informed Correctors for Discrete Diffusion Models
- One-Step Offline Distillation of Diffusion-based Models via Koopman Modeling