SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical Zoom

04/02/2021
by   Kangfu Mei, et al.
0

Deep Neural Network (DNN) based super-resolution algorithms have greatly improved the quality of the generated images. However, these algorithms often yield significant artifacts when dealing with real-world super-resolution problems due to the difficulty in learning misaligned optical zoom. In this paper, we introduce a Squared Deformable Alignment Network (SDAN) to address this issue. Our network learns squared per-point offsets for convolutional kernels, and then aligns features in corrected convolutional windows based on the offsets. So the misalignment will be minimized by the extracted aligned features. Different from the per-point offsets used in the vanilla Deformable Convolutional Network (DCN), our proposed squared offsets not only accelerate the offset learning but also improve the generation quality with fewer parameters. Besides, we further propose an efficient cross packing attention layer to boost the accuracy of the learned offsets. It leverages the packing and unpacking operations to enlarge the receptive field of the offset learning and to enhance the ability of extracting the spatial connection between the low-resolution images and the referenced images. Comprehensive experiments show the superiority of our method over other state-of-the-art methods in both computational efficiency and realistic details.

READ FULL TEXT

page 3

page 5

research
09/24/2019

Deformable Non-local Network For Video Super-Resolution

The video super-resolution (VSR) task aims to restore a high-resolution ...
research
10/01/2020

Deformable Kernel Convolutional Network for Video Extreme Super-Resolution

Video super-resolution, which attempts to reconstruct high-resolution vi...
research
04/18/2022

BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment

This work addresses the Burst Super-Resolution (BurstSR) task using a ne...
research
05/26/2020

Perceptual Extreme Super Resolution Network with Receptive Field Block

Perceptual Extreme Super-Resolution for single image is extremely diffic...
research
02/03/2022

Fast Online Video Super-Resolution with Deformable Attention Pyramid

Video super-resolution (VSR) has many applications that pose strict caus...
research
04/29/2023

An Implicit Alignment for Video Super-Resolution

Video super-resolution commonly uses a frame-wise alignment to support t...
research
06/01/2022

Efficient Multi-Purpose Cross-Attention Based Image Alignment Block for Edge Devices

Image alignment, also known as image registration, is a critical block u...

Please sign up or login with your details

Forgot password? Click here to reset