Awesome-Deblurring-Resources

一个精选的与图像和视频去模糊相关的研究论文和数据集列表。

A curated list of research papers and datasets related to image and video deblurring.

原始信息汇总

Awesome-Deblurring-Resources 数据集概述

数据集列表

以下是与图像和视频去模糊相关的精选数据集列表：

• 2024 Papers

  • Blind Image Deblurring using FFT-ReLU with Deep Learning Pipeline Integration
  • Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution
  • Estimation of motion blur kernel parameters using regression convolutional neural networks
  • A Unified Framework for Microscopy Defocus Deblur with Multi-Pyramid Transformer and Contrastive Learning
  • AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring
  • Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains
  • Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring
  • ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation
  • LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network
  • Mitigating Motion Blur in Neural Radiance Fields with Events and Frames
  • Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring
  • Motion Blur Decomposition with Cross-shutter Guidance
  • Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment
  • Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring
  • Unsupervised Blind Image Deblurring Based on Self-Enhancement
  • Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization
  • EVS-assisted Joint Deblurring Rolling-Shutter Correction and Video Frame Interpolation through Sensor Inverse Modeling
  • Latency Correction for Event-guided Deblurring and Frame Interpolation
  • Frequency-aware Event-based Video Deblurring for Real-World Motion Blur
  • Gyroscope-Assisted Motion Deblurring Network
  • Gyro-based Neural Single Image Deblurring
  • BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting
  • BeNeRF: Neural Radiance Fields from a Single Blurry Image and Event Stream
  • Blind image deblurring with noise-robust kernel estimation
  • Domain-adaptive Video Deblurring via Test-time Blurring
  • Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion
  • Towards Real-world Event-guided Low-light Video Enhancement and Deblurring
  • UniINR: Event-guided Unified Rolling Shutter Correction, Deblurring, and Interpolation

• 2023 Papers

  • GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration
  • Blind Image Deblurring with Unknown Kernel Size and Substantial Noise
  • INFWIDE: Image and Feature Space Wiener Deconvolution Network for Non-blind Image Deblurring in Low-Light Conditions
  • Real-World Deep Local Motion Deblurring
  • Multi-scale Residual Low-Pass Filter Network for Image Deblurring
  • Multi-Scale Frequency Separation Network for Image Deblurring
  • IRNeXt: Rethinking Convolutional Network Design for Image Restoration
  • Structured Kernel Estimation for Photon-Limited Deconvolution
  • Blur Interpolation Transformer for Real-World Motion from Blur
  • Neumann Network with Recursive Kernels for Single Image Defocus Deblurring
  • Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring
  • Hybrid Neural Rendering for Large-Scale Scenes with Motion Blur
  • Self-Supervised Non-Uniform Kernel Estimation With Flow-Based Motion Prior for Blind Image Deblurring
  • Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior
  • K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring
  • Self-Supervised Blind Motion Deblurring With Deep Expectation Maximization
  • HyperCUT: Video Sequence from a Single Blurry Image using Unsupervised Ordering
  • Deep Discriminative Spatial and Temporal Network for Efficient Video Deblurring
  • Dual-Domain Attention for Image Deblurring
  • Real-World Deep Local Motion Deblurring
  • Learning Single Image Defocus Deblurring with Misaligned Training Pairs
  • Intriguing Findings of Frequency Selection for Image Deblurring
  • Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild
  • Multiscale Structure Guided Diffusion for Image Deblurring
  • Single Image Defocus Deblurring via Implicit Neural Inverse Kernels
  • Single Image Deblurring with Row-dependent Blur Magnitude
  • Non-Coaxial Event-Guided Motion Deblurring with Spatial Alignment
  • Generalizing Event-Based Motion Deblurring in Real-World Scenarios
  • Exploring Temporal Frequency Spectrum in Deep Video Deblurring
  • Hierarchical Integration Diffusion Model for Realistic Image Deblurring
  • Enhancing Motion Deblurring in High-Speed Scenes with Spike Streams

• 2022 Papers

  • MSSNet: Multi-Scale-Stage Network for Single Image Deblurring
  • HINet: Half Instance Normalization Network for Image Restoration
  • BANet: A Blur-Aware Attention Network for Dynamic Scene Deblurring
  • Learning to Deblur using Light Field Generated and Real Defocus Images
  • Pixel Screening Based Intermediate Correction for Blind Deblurring
  • Deblurring via Stochastic Refinement
  • XYDeblur: Divide and Conquer for Single Image Deblurring
  • Unifying Motion Deblurring and Frame Interpolation with Events
  • E-CIR: Event-Enhanced Continuous Intensity Recovery
  • Multi-Scale Memory-Based Video Deblurring
  • Learning Degradation Representations for Image Deblurring
  • Stripformer: Strip Transformer for Fast Image Deblurring
  • Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance
  • United Defocus Blur Detection and Deblurring via Adversarial Promoting Learning
  • Realistic Blur Synthesis for Learning Image Deblurring
  • Event-based Fusion for Motion Deblurring with Cross-modal Attention
  • Event-Guided Deblurring of Unknown Exposure Time Videos
  • Spatio-Temporal Deformable Attention Network for Video Deblurring
  • Efficient Video Deblurring Guided by Motion Magnitude
  • ERDN: Equivalent Receptive Field Deformable Network for Video Deblurring
  • DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting
  • Towards Real-World Video Deblurring by Exploring Blur Formation Process

• 2021 Papers

  • Explore Image Deblurring via Encoded Blur Kernel Space
  • Rethinking Coarse-to-Fine Approach in Single Image Deblurring
  • Multi-Stage Progressive Image Restoration

搜集汇总

数据集介绍

构建方式

Awesome-Deblurring-Resources数据集的构建基于对图像和视频去模糊领域的深入研究。该数据集精心收集了自2019年以来的相关研究论文和数据集，涵盖了多个顶级会议和期刊的最新成果。通过系统地整理和分类，数据集构建者确保了资源的全面性和时效性，为研究人员提供了丰富的参考资料。

特点

该数据集的显著特点在于其全面性和多样性。它不仅包含了大量的研究论文，还提供了多个与去模糊相关的数据集链接，涵盖了从图像到视频的多种应用场景。此外，数据集还特别关注了不同年份的研究进展，使得用户能够追踪该领域的最新动态和技术演进。

使用方法

使用Awesome-Deblurring-Resources数据集时，用户可以根据年份和会议分类快速定位感兴趣的论文。对于需要特定数据集进行实验的研究者，可以直接访问README文件中提供的链接获取相关资源。此外，数据集还提供了代码链接，方便用户直接获取和复现相关研究成果。

背景与挑战

背景概述

图像去模糊技术在计算机视觉领域具有重要意义，旨在从模糊图像中恢复清晰内容。Awesome-Deblurring-Resources数据集由一群专注于图像和视频去模糊研究的研究人员和机构精心策划，涵盖了从2019年到2024年的大量研究论文和相关数据集。该数据集的创建旨在为去模糊技术的研究提供一个全面的资源库，支持研究人员在图像和视频去模糊领域的探索与创新。通过整理和分类这些资源，数据集不仅展示了去模糊技术的最新进展，还为未来的研究提供了坚实的基础。

当前挑战

尽管Awesome-Deblurring-Resources数据集为去模糊研究提供了丰富的资源，但仍面临若干挑战。首先，去模糊技术的核心问题在于如何准确估计和去除图像中的模糊，这需要高精度的算法和模型。其次，数据集的构建过程中，如何确保数据的质量和多样性，以反映真实世界的复杂情况，是一个重要挑战。此外，随着深度学习技术的发展，如何在保持模型高效性的同时，提升去模糊效果，也是当前研究的一个难点。最后，跨领域的融合，如结合事件相机数据进行去模糊，为技术带来了新的可能性，但也增加了研究的复杂性。

常用场景

经典使用场景

在图像处理领域，Awesome-Deblurring-Resources数据集被广泛应用于图像去模糊任务。该数据集汇集了大量与图像和视频去模糊相关的研究论文和数据集，为研究人员提供了一个全面的资源库。经典的使用场景包括但不限于：利用深度学习技术对模糊图像进行恢复，通过多尺度分析和时空变换网络来提升去模糊效果，以及在不同光照和运动条件下进行图像去模糊实验。

实际应用

在实际应用中，Awesome-Deblurring-Resources数据集的应用场景广泛且多样化。例如，在监控和安全领域，通过去模糊技术可以提高视频监控画面的清晰度，增强识别和追踪能力。在自动驾驶和机器人视觉中，去模糊技术有助于提升视觉系统的鲁棒性和准确性，确保在复杂环境中的可靠操作。此外，在摄影和影视制作中，该数据集支持开发更高效的去模糊工具，提升图像和视频的质量，满足专业和消费级市场的需求。

衍生相关工作

Awesome-Deblurring-Resources数据集不仅自身是一个重要的研究资源，还衍生出了一系列经典的工作。例如，基于该数据集的研究成果，开发了多种先进的去模糊算法，如利用深度学习进行盲去模糊的模型、结合事件相机数据的去模糊方法等。这些工作不仅在学术界引起了广泛关注，也在工业界得到了实际应用，推动了图像处理技术的进步。此外，该数据集还促进了多模态数据融合的研究，如将图像与事件数据结合，为解决复杂场景下的去模糊问题提供了新的思路和方法。