paper-with-me

Papers

Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks

2019-07-30 · Rajeev Yasarla, Federico Perazzi, Vishal M. Patel

We propose a novel multi-stream architecture and training methodology that exploits semantic labels for facial image deblurring. The proposed Uncertainty Guided Multi- Stream Semantic Network (UMSN) processes regions belonging to each semantic class independently and learns to combine their outputs into the final deblurred result. Pixel-wise semantic labels are obtained using a segmentation network. A predicted confidence measure is used during training to guide the network towards the challenging regions of the human face such as the eyes and nose. The entire network is trained in an end- to-end fashion. Comprehensive experiments on three different face datasets demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art face deblurring methods. Code is available at: https://github.com/ rajeevyasarla/UMSN-Face-Deblurring

📄 PDF Abstract BibTeX arXiv:1907.13106

Code (1)

rajeevyasarla/UMSN-Face-Deblurring 공식 구현 pytorch

Tasks

DeblurringImage Deblurring

Similar Papers 제목 키워드 기반

Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement

2018-11-22 · Yibing Song, Jiawei Zhang, Lijun Gong, Shengfeng He 외

We address the problem of restoring a high-resolution face image from a blurry low-resolution input. This problem is difficult as super-resolution and deblurring need to be tackled simultaneously. Moreover, existing algo…

DeblurringFace HallucinationHallucinationSuper-Resolution

Event-guided Multi-patch Network with Self-supervision for Non-uniform Motion Deblurring

2023-02-14 · Hongguang Zhang, Limeng Zhang, Yuchao Dai, Hongdong Li 외

Contemporary deep learning multi-scale deblurring models suffer from many issues: 1) They perform poorly on non-uniformly blurred images/videos; 2) Simply increasing the model depth with finer-scale levels cannot improve…

Deblurring

Variational-EM-Based Deep Learning for Noise-Blind Image Deblurring

2020-06-01 · CVPR 2020 6 · Yuesong Nan, Yuhui Quan, Hui Ji

Non-blind deblurring is an important problem encountered in many image restoration tasks. The focus of non-blind deblurring is on how to suppress noise magnification during deblurring. In practice, it often happens that …

Blind Image DeblurringDeblurringDeep LearningImage Deblurring+2

Learning to Deblur Images with Exemplars

2018-05-15 · Jinshan Pan, Wenqi Ren, Zhe Hu, Ming-Hsuan Yang

Human faces are one interesting object class with numerous applications. While significant progress has been made in the generic deblurring problem, existing methods are less effective for blurry face images. The success…

DeblurringImage Deblurring

Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment

2024-01-01 · CVPR 2024 1 · Jiyuan Zhang, Shiyan Chen, Yajing Zheng, Zhaofei Yu 외

The traditional frame-based cameras that rely on exposure windows for imaging experience motion blur in high-speed scenarios. Frame-based deblurring methods lack reliable motion cues to restore sharp images under ext…

DeblurringImage Deblurring