paper-with-me

Image Deblurring

9개 벤치마크 · 논문 434편 · 이 태스크의 논문 보기 →

Benchmarks

GoPro

결과 275개

HIDE

결과 25개

CelebA

결과 15개

ImageNet

결과 15개

Real-world Dataset

결과 5개

RealBlur-J

결과 5개

RealBlur-R

결과 5개

Most implemented

Simple Baselines for Image Restoration

2022-04-10 · 구현 13개

Multi-Stage Progressive Image Restoration

2021-02-04 · 구현 8개

Papers

GS-RealBlur: A Flexible Data Acquisition Framework for Real-World Image Deblurring

2026-07-16 · Mingyang Chen, Zhilu Zhang, Honglei Xu, Renlong Wu 외 arxiv

High-quality, large-scale paired data is essential for training learning-based image deblurring models. However, synthetic blurry images generally lack realism, while real-world captured images require complex and inflex…

Image Deblurring

DICT: Data Injection and Contrastive Trajectory Refinement for Conditional Image Generation with Diffusion Models

2026-07-04 · Chunnan Shang, Xin Zhang, Zhizhong Wang, Hongwei Wang arxiv

Diffusion models have become a dominant paradigm for conditional image generation, yet existing approaches generally follow two directions: task-specific designs that can improve performance but limit generalization, and…

Conditional Image GenerationImage Super-ResolutionImage DeblurringStyle Transfer

Leveraging Phase Information to Boost Unrolled Network Learning for Image Deblurring

2026-06-30 · Samira Malek, Haichuan Zhang, Chul Lee, Vishal Monga arxiv

While most image deblurring techniques directly restore the spatial image variable, we propose an amplitude and phase decomposition recognizing the importance of accurate phase estimation in recovering sharp image detail…

Image Deblurring

CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion

2026-06-29 · Pan Wang, Yihao Hu, Xiujin Liu hf

Blind image deblurring demands the recovery of high-fidelity details and coherent structures from complex, unknown degradations. Current blind image deblurring methods struggle with real-world, spatially varying degradat…

Image Deblurring

FSM-Net: An Efficient Frequency-Spatial Network for Real-World Deblurring

2026-05-29 · Vinh-Thuan Ly arxiv

Real-world image deblurring demands both high-fidelity restoration and computational efficiency, a balance existing methods often struggle to achieve. In this paper, we propose FSM-Net (Frequency-Spatial Multi-branch Net…

Computational EfficiencyImage RestorationImage Deblurring

Stop Denoising Your Blurs

2026-05-24 · Sasidhar Parvathireddy, Vamsidhar Saraswathula, Rama Krishna Gorthi arxiv

In recent times, diffusion models have achieved remarkable performance in image restoration tasks. Their core mechanism relies on the restricted presumption of degradation prior to the additive noise operation. However, …

Image RestorationImage Deblurring

전체 434편 보기 →