A strong baseline for image and video quality assessment

11/13/2021
by   Shaoguo Wen, et al.
0

In this work, we present a simple yet effective unified model for perceptual quality assessment of image and video. In contrast to existing models which usually consist of complex network architecture, or rely on the concatenation of multiple branches of features, our model achieves a comparable performance by applying only one global feature derived from a backbone network (i.e. resnet18 in the presented work). Combined with some training tricks, the proposed model surpasses the current baselines of SOTA models on public and private datasets. Based on the architecture proposed, we release the models well trained for three common real-world scenarios: UGC videos in the wild, PGC videos with compression, Game videos with compression. These three pre-trained models can be directly applied for quality assessment, or be further fine-tuned for more customized usages. All the code, SDK, and the pre-trained weights of the proposed models are publicly available at https://github.com/Tencent/CenseoQoE.

READ FULL TEXT
research
11/09/2020

Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training

Video quality assessment (VQA) is an important problem in computer visio...
research
08/01/2019

Quality Assessment of In-the-Wild Videos

Quality assessment of in-the-wild videos is a challenging problem becaus...
research
05/08/2023

Compressed Video Quality Assessment for Super-Resolution: a Benchmark and a Quality Metric

We developed a super-resolution (SR) benchmark to analyze SR's capacity ...
research
07/08/2022

Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessment

With the rapid growth of in-the-wild videos taken by non-specialists, bl...
research
08/19/2021

Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception

Perceptual quality assessment of the videos acquired in the wilds is of ...
research
08/10/2020

Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessment

Currently, most image quality assessment (IQA) models are supervised by ...
research
06/09/2023

GMS-3DQA: Projection-based Grid Mini-patch Sampling for 3D Model Quality Assessment

Nowadays, most 3D model quality assessment (3DQA) methods have been aime...

Please sign up or login with your details

Forgot password? Click here to reset