UGC-VIDEO: Perceptual Quality Assessment of User-Generated Videos

Abstract

Recent years have witnessed an exponential increase in the demand for face video compression, and the success of artificial intelligence has expanded the boundaries beyond traditional hybrid video coding. Generative coding approaches have been identified as promising alternatives with reasonable perceptual rate-distortion trade-offs, leveraging the statistical priors of face videos. However, the great diversity of distortion types in spatial and temporal domains, ranging from the traditional hybrid coding frameworks to generative models, present grand challenges in compressed face video quality assessment (VQA) that plays a crucial role in the whole delivery chain for quality monitoring and optimization. In this paper, we introduce the large-scale Compressed Face Video Quality Assessment (CFVQA) database, which is the first attempt to systematically understand the perceptual quality and diversified compression distortions in face videos. The database contains 3,240 compressed face video clips in multiple compression levels, which are derived from 135 source videos with diversified content using six representative video codecs, including two traditional methods based on hybrid coding frameworks, two end-to-end methods, and two generative methods. The unique characteristics of CFVQA, including large-scale, fine-grained, great content diversity, and cross-compression distortion types, make the benchmarking for existing image quality assessment (IQA) and VQA feasible and practical. The results reveal the weakness of existing IQA and VQA models, posing challenges on real-world face video applications. In addition, a FAce VideO IntegeRity (FAVOR) index for face video compression was developed to measure the perceptual quality, considering the distinct content characteristics and temporal priors of the face videos. Experimental results exhibit its superior performance on the proposed CFVQA dataset. The benchmark is now made publicly available at: https://github.com/Yixuan423/Compressed-Face-Videos-Quality-Assessment.

Subjective and Objective Analysis of Streamed Gaming Videos

“…Many recent (non-gaming) UGC video quality databases [15], [38], [39], [48] were created by harvesting a large number of source videos from one or more large free public video repositories, such as the Internet Archive [49] or YFCC-100M [16]. These are typically "winnowed" to a set of videos that are representative of a category of interest, such as social media videos.…”

Study of Subjective and Objective Quality Assessment of Night-Time Videos

“…Depending on the usage of the pristine reference video, VQA algorithms can be classified into three types, i.e., full-reference (FR), reduced-reference (RR), and no-reference (NR). In the absence of pristine reference for the in-capture content, NR-VQA models [1][2][3][4][5][6][7][8][9][10] which rely only on the impaired videos are most appropriate [11][12][13][14].…”

An Efficient Method for No-Reference Video Quality Assessment

“…The automatic estimation of the quality of a UGC as perceived by human observers is fundamental for a wide range of applications. For example, to discriminate professional and amateur video content on user-generated video distribution platforms [ 1 ], to choose the best sequence among many sequences for sharing in social media [ 2 ], to guide a video enhancement process [ 3 ], and to rank/choose user-generated videos [ 4 , 5 ].…”