DeepAI
Log In Sign Up

Towards True Detail Restoration for Super-Resolution: A Benchmark and a Quality Metric

03/16/2022
by   Eugene Lyapustin, et al.
0

Super-resolution (SR) has become a widely researched topic in recent years. SR methods can improve overall image and video quality and create new possibilities for further content analysis. But the SR mainstream focuses primarily on increasing the naturalness of the resulting image despite potentially losing context accuracy. Such methods may produce an incorrect digit, character, face, or other structural object even though they otherwise yield good visual quality. Incorrect detail restoration can cause errors when detecting and identifying objects both manually and automatically. To analyze the detail-restoration capabilities of image and video SR models, we developed a benchmark based on our own video dataset, which contains complex patterns that SR models generally fail to correctly restore. We assessed 32 recent SR models using our benchmark and compared their ability to preserve scene context. We also conducted a crowd-sourced comparison of restored details and developed an objective assessment metric that outperforms other quality metrics by correlation with subjective scores for this task. In conclusion, we provide a deep analysis of benchmark results that yields insights for future SR-based work.

READ FULL TEXT

page 2

page 3

page 6

page 9

10/19/2021

ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution

Despite the growing popularity of video super-resolution (VSR), there is...
04/30/2021

NTIRE 2021 Challenge on Video Super-Resolution

Super-Resolution (SR) is a fundamental computer vision task that aims to...
10/12/2022

QMRNet: Quality Metric Regression for EO Image Quality Assessment and Super-Resolution

Latest advances in Super-Resolution (SR) have been tested with general p...
05/27/2022

Textural-Structural Joint Learning for No-Reference Super-Resolution Image Quality Assessment

Image super-resolution (SR) has been widely investigated in recent years...
11/15/2022

CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streaming

Recent years have witnessed the dramatic growth of Internet video traffi...