Deep Video Deblurring

Abstract

Motion blur from camera shake is a major problem in videos captured by hand-held devices. Unlike single-image deblurring, video-based approaches can take advantage of the abundant information that exists across neighboring frames. As a result the best performing methods rely on aligning nearby frames. However, aligning images is a computationally expensive and fragile procedure, and methods that aggregate information must therefore be able to identify which regions have been accurately aligned and which have not, a task which requires high level scene understanding. In this work, we introduce a deep learning solution to video deblurring, where a CNN is trained end-to-end to learn how to accumulate information across frames. To train this network, we collected a dataset of real videos recorded with a high framerate camera, which we use to generate synthetic motion blur for supervision. We show that the features learned from this dataset extend to deblurring motion blur that arises due to camera shake in a wide range of videos, and compare the quality of results to a number of other baselines.

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Deep Residual Learning for Image Recognition
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• FlowNet: Learning Optical Flow with Convolutional Networks
• Lucky Imaging: High Angular Resolution Imaging in the Visible from the Ground
• Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal
• Recent Progress in Image Deblurring
• A Neural Approach to Blind Motion Deblurring
• Generalized Video Deblurring for Dynamic Scenes
• Dynamic Scene Deblurring using a Locally Adaptive Linear Blur Model

Cited by in corpus (13)

• DeepISP: Towards Learning an End-to-End Image Processing Pipeline
• Bridging the Gap Between Computational Photography and Visual Recognition
• Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
• Learning Deformable Kernels for Image and Video Denoising
• Detail-revealing Deep Video Super-resolution
• Burst Denoising with Kernel Prediction Networks
• Online Video Deblurring via Dynamic Temporal Blending Network
• Scale-recurrent Network for Deep Image Deblurring
• Deep Online Video Stabilization
• Reblur2Deblur: Deblurring Videos via Self-Supervised Learning
• Report on UG^2+ Challenge Track 1: Assessing Algorithms to Improve Video Object Detection and Classification from Unconstrained Mobility Platforms
• cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey
• Video Deblurring via Semantic Segmentation and Pixel-Wise Non-Linear Kernel