generative priors
Generative priors are assumptions or distributions about the underlying data generation processes integrated into generative models. They play a key role in defining how models synthesize new data points based on learned patterns.
- 3DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization
- Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior
- HoloScene: Simulation‑Ready Interactive 3D Worlds from a Single Video
- How many measurements are enough? Bayesian recovery in inverse problems with general distributions
- MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding
- OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates
- PanoWan: Lifting Diffusion Video Generation Models to 360$^\circ$ with Latitude/Longitude-aware Mechanisms
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
- PocketSR: The Super-Resolution Expert in Your Pocket Mobiles
- Projection-Manifold Regularized Latent Diffusion for Robust General Image Fusion
- Solving Inverse Problems with FLAIR