DeepAI AI Chat
Log In Sign Up

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

by   Anastasia Kirillova, et al.
Lomonosov Moscow State University

Despite the growing popularity of video super-resolution (VSR), there is still no good way to assess the quality of the restored details in upscaled frames. Some SR methods may produce the wrong digit or an entirely different face. Whether a method's results are trustworthy depends on how well it restores truthful details. Image super-resolution can use natural distributions to produce a high-resolution image that is only somewhat similar to the real one. VSR enables exploration of additional information in neighboring frames to restore details from the original scene. The ERQA metric, which we propose in this paper, aims to estimate a model's ability to restore real details using VSR. On the assumption that edges are significant for detail and character recognition, we chose edge fidelity as the foundation for this metric. Experimental validation of our work is based on the MSU Video Super-Resolution Benchmark, which includes the most difficult patterns for detail restoration and verifies the fidelity of details from the original frame. Code for the proposed metric is publicly available at


page 1

page 2

page 3

page 4

page 6

page 8


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

Super-resolution (SR) has become a widely researched topic in recent yea...

An Efficient Network Design for Face Video Super-resolution

Face video super-resolution algorithm aims to reconstruct realistic face...

Image Super-Resolution Quality Assessment: Structural Fidelity Versus Statistical Naturalness

Single image super-resolution (SISR) algorithms reconstruct high-resolut...

VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution

Most of the existing video face super-resolution (VFSR) methods are trai...

A Novel Dual Dense Connection Network for Video Super-resolution

Video super-resolution (VSR) refers to the reconstruction of high-resolu...

Mitigating Artifacts in Real-World Video Super-Resolution Models

The recurrent structure is a prevalent framework for the task of video s...

Combining Contrastive and Supervised Learning for Video Super-Resolution Detection

Upscaled video detection is a helpful tool in multimedia forensics, but ...