Lipschitz-Controlled Flow Matching for Robust Image Restoration
cs.CV
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/sczhou/CodeFormer
Terminology
Sources
- Efficient Image Restoration via Latent Consistency Flow Matching
- Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers
- IR-Flow: Bridging Discriminative and Generative Image Restoration via Rectified Flow
- BayesFlow 2: Multi-Backend Amortized Bayesian Inference in Python
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Decoupled Weight Decay Regularization
- Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration
- GLU Variants Improve Transformer
- Adversarial Lipschitz Regularization
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs