Deep Stacked Hierarchical Multi-patch Network for Image Deblurring

04/06/2019
by   Hongguang Zhang, et al.
0

Despite deep end-to-end learning methods have shown their superiority in removing non-uniform motion blur, there still exist major challenges with the current multi-scale and scale-recurrent models: 1) Deconvolution/upsampling operations in the coarse-to-fine scheme result in expensive runtime; 2) Simply increasing the model depth with finer-scale levels cannot improve the quality of deblurring. To tackle the above problems, we present a deep hierarchical multi-patch network inspired by Spatial Pyramid Matching to deal with blurry images via a fine-to-coarse hierarchical representation. To deal with the performance saturation w.r.t. depth, we propose a stacked version of our multi-patch model. Our proposed basic multi-patch model achieves the state-of-the-art performance on the GoPro dataset while enjoying a 40x faster runtime compared to current multi-scale methods. With 30ms to process an image at 1280x720 resolution, it is the first real-time deep motion deblurring model for 720p images at 30fps. For stacked networks, significant improvements (over 1.2dB) are achieved on the GoPro dataset by increasing the network depth. Moreover, by varying the depth of the stacked model, one can adapt the performance and runtime of the same network for different application scenarios.

READ FULL TEXT

page 2

page 5

page 8

page 9

research
02/14/2023

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

Contemporary deep learning multi-scale deblurring models suffer from man...
research
05/12/2020

Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing

Recently, CNN based end-to-end deep learning methods achieve superiority...
research
05/15/2021

Stacked Deep Multi-Scale Hierarchical Network for Fast Bokeh Effect Rendering from a Single Image

The Bokeh Effect is one of the most desirable effects in photography for...
research
07/11/2019

Edge Heuristic GAN for Non-uniform Blind Deblurring

Non-uniform blur, mainly caused by camera shake and motions of multiple ...
research
06/20/2019

SGANVO: Unsupervised Deep Visual Odometry and Depth Estimation with Stacked Generative Adversarial Networks

Recently end-to-end unsupervised deep learning methods have achieved an ...
research
04/11/2020

Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring

This paper tackles the problem of motion deblurring of dynamic scenes. A...
research
07/13/2021

MSR-Net: Multi-Scale Relighting Network for One-to-One Relighting

Deep image relighting allows photo enhancement by illumination-specific ...

Please sign up or login with your details

Forgot password? Click here to reset