Cover Image

Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Xiaogang, Chu, Ruihang, Wang, Jian, Zhou, Kun, Shu, Wenjie, Yang, Harry, Lim, Ser-Nam, Chen, Hao, Lin, Liang
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards Unified 3D Object Detection via Algorithm and Data Unification
by: Li, Zhuoling, et al.
Published: (2024)

Beyond Generation: Unlocking Universal Editing via Self-Supervised Fine-Tuning
by: Chen, Harold Haodong, et al.
Published: (2024)

Boosting Fidelity for Pre-Trained-Diffusion-Based Low-Light Image Enhancement via Condition Refinement
by: Xu, Xiaogang, et al.
Published: (2025)

VideoMerge: Towards Training-free Long Video Generation
by: Zhang, Siyang, et al.
Published: (2025)

LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence
by: Li, Zhuoling, et al.
Published: (2024)

Towards Chunk-Wise Generation for Long Videos
by: Zhang, Siyang, et al.
Published: (2024)

Zero-shot Synthetic Video Realism Enhancement via Structure-aware Denoising
by: Wang, Yifan, et al.
Published: (2025)

Fast Encoding and Decoding for Implicit Video Representation
by: Chen, Hao, et al.
Published: (2024)

Video Decomposition Prior: A Methodology to Decompose Videos into Layers
by: Shrivastava, Gaurav, et al.
Published: (2024)

Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning
by: Park, Dongmin, et al.
Published: (2024)

Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation
by: Chen, Harold Haodong, et al.
Published: (2025)

DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
by: Zhou, Yang, et al.
Published: (2026)

PR-IQA: Partial-Reference Image Quality Assessment for Diffusion-Based Novel View Synthesis
by: Choi, Inseong, et al.
Published: (2026)

Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models
by: Ma, Xuran, et al.
Published: (2025)

DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback Learning
by: Wu, Bin, et al.
Published: (2025)

AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer
by: Fang, Pengjun, et al.
Published: (2026)

Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View
by: Wu, Xianzu, et al.
Published: (2025)

DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness
by: Mohammadshirazi, Ahmad, et al.
Published: (2024)

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding
by: Shu, Yan, et al.
Published: (2025)

AgenticIQA: An Agentic Framework for Adaptive and Interpretable Image Quality Assessment
by: Zhu, Hanwei, et al.
Published: (2025)

STUDY ON PREPARATION AND PROPERTIES OF PHENOL-FORMALDEHYDE-CHINESE FIR LIQUEFACTION COPOLYMER RESIN
by: Ruihang Lin
Published: (2014)

VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention
by: Zheng, Mingzhe, et al.
Published: (2025)

VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention
by: Zheng, Mingzhe, et al.
Published: (2024)

BOOKAGENT: Orchestrating Safety-Aware Visual Narratives via Multi-Agent Cognitive Calibration
by: Gao, Bo, et al.
Published: (2026)

CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation
by: Zheng, Mingzhe, et al.
Published: (2025)

Boosting Image Restoration via Priors from Pre-trained Models
by: Xu, Xiaogang, et al.
Published: (2024)

AirSketch: Generative Motion to Sketch
by: Lim, Hui Xian Grace, et al.
Published: (2024)

LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision
by: Huang, Jiani, et al.
Published: (2023)

DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data
by: Tu, Yuanpeng, et al.
Published: (2025)

Composing Object Relations and Attributes for Image-Text Matching
by: Pham, Khoi, et al.
Published: (2024)

Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop
by: Qian, Zhaofang, et al.
Published: (2024)

Delta Activations: A Representation for Finetuned Large Language Models
by: Xu, Zhiqiu, et al.
Published: (2025)

Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning
by: Liang, Guoqiang, et al.
Published: (2026)

Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning
by: Monsefi, Amin Karimi, et al.
Published: (2024)

From Global to Granular: Revealing IQA Model Performance via Correlation Surface
by: Chen, Baoliang, et al.
Published: (2026)

SA-IQA: Redefining Image Quality Assessment for Spatial Aesthetics with Multi-Dimensional Rewards
by: Gao, Yuan, et al.
Published: (2025)

Temporal Regularization Makes Your Video Generator Stronger
by: Chen, Harold Haodong, et al.
Published: (2025)

EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO
by: Guan, Wei, et al.
Published: (2025)

ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking
by: Fan, Kanglong, et al.
Published: (2026)

Unlocking Multimodal Mathematical Reasoning via Process Reward Model
by: Luo, Ruilin, et al.
Published: (2025)