ODDR: One-Step Deshadow Diffusion via Reward Guidance
cs.CV
Submitted: 2026-10-01
Updated: 2026-10-01
Terminology
Sources
- Qwen2.5-VL Technical Report
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal
- Classifier-Free Diffusion Guidance
- One-Step Diffusion Model for Image Motion-Deblurring
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Decoupled Weight Decay Regularization
- DINOv2: Learning Robust Visual Features without Supervision
- RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought
- DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback Learning
- DP$^2$O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
- Fine-Tuning Language Models from Human Preferences
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models