UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution

03/23/2021
by   Xingqian Xu, et al.
0

The recent success of NeRF and other related implicit neural representation methods has opened a new path for continuous image representation, where pixel values no longer need to be looked up from stored discrete 2D arrays but can be inferred from neural network models on a continuous spatial domain. Although the recent work LIIF has demonstrated that such novel approach can achieve good performance on the arbitrary-scale super-resolution task, their upscaled images frequently show structural distortion due to the faulty prediction on high-frequency textures. In this work, we propose UltraSR, a simple yet effective new network design based on implicit image functions in which spatial coordinates and periodic encoding are deeply integrated with the implicit neural representation. We show that spatial encoding is indeed a missing key towards the next-stage high-accuracy implicit image function through extensive experiments and ablation studies. Our UltraSR sets new state-of-the-art performance on the DIV2K benchmark under all super-resolution scales comparing to previous state-of-the-art methods. UltraSR also achieves superior performance on other standard benchmark datasets in which it outperforms prior works in almost all experiments. Our code will be released at https://github.com/SHI-Labs/UltraSR-Arbitrary-Scale-Super-Resolution.

READ FULL TEXT

page 1

page 4

page 7

research
08/07/2022

Adaptive Local Implicit Image Function for Arbitrary-scale Super-resolution

Image representation is critical for many visual tasks. Instead of repre...
research
12/20/2021

Implicit Neural Representation Learning for Hyperspectral Image Super-Resolution

Hyperspectral image (HSI) super-resolution without additional auxiliary ...
research
06/21/2023

Dynamic Implicit Image Function for Efficient Arbitrary-Scale Image Representation

Recent years have witnessed the remarkable success of implicit neural re...
research
09/04/2023

Implicit Neural Image Stitching With Enhanced and Blended Feature Reconstruction

Existing frameworks for image stitching often provide visually reasonabl...
research
12/07/2022

Learning Continuous Depth Representation via Geometric Spatial Aggregator

Depth map super-resolution (DSR) has been a fundamental task for 3D comp...
research
03/05/2023

Super-Resolution Neural Operator

We propose Super-resolution Neural Operator (SRNO), a deep operator lear...
research
11/07/2022

Image Completion with Heterogeneously Filtered Spectral Hints

Image completion with large-scale free-form missing regions is one of th...

Please sign up or login with your details

Forgot password? Click here to reset