UVG dataset: 50/120fps 4K sequences for video codec analysis and development

By Alexandre Mercat, Marko Viitanen, Jarno Vanne. ACM SIGMM Conference on Multimedia Systems, 2020

642 citations recorded by the source corpus.

This paper provides an overview of our open Ultra Video Group (UVG) dataset that is composed of 16 versatile 4K (3840×2160) test video sequences. These natural sequences were captured either at 50 or 120 frames per second (fps) and stored online in raw 8-bit and 10-bit 4:2:0 YUV formats. The dataset is published on our website (ultravideo.cs.tut.fi) under a non-commercial Creative Commons BY-NC license. In this paper, all UVG sequences are described in detail and characterized by their spatial and temporal perceptual information, rate-distortion behavior, and coding complexity with the latest HEVC/H.265 and VVC/H.266 reference video codecs. The proposed dataset is the first to provide complementary 4K sequences up to 120 fps and is therefore particularly valuable for cutting-edge multimedia applications. Our evaluations also show that it comprehensively complements the existing 4K test set in VVC standardization, so we recommend including it in subjective and objective quality assessments of next-generation VVC codecs.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/4f5c5f128a8bc1562acf90acd2d3b364eb0c6512

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Ser-Nam Lim
2. Bin Li
3. Yan Lu
4. Dong Xu
5. Jiahao Li
6. Luc Van Gool
7. Trevor Darrell
8. Dacheng Tao

In Signal Processing

1. Jiahao Li
2. Yan Lu
3. Bin Li
4. Guo Lu
5. Yixuan Ren
6. Abhinav Shrivastava
7. Bo He
8. Zhihao Hu

Citations in the corpus

• Neural Video Compression with Diverse Contexts (2023, methodology): “For testing YUV420 videos, HEVC B∼E [6], UVG [39], and MCL-JCV [57] are used.”
• NeRV: Neural Representations for Videos (2021, methodology): “We conduct extensive experiments on popular video compression datasets, such as UVG [7], and show the applicability of model compression techniques on NeRV for video compression.”
• FVC: A New Framework towards Deep Video Compression in Feature Space (2021, methodology): “In this section, we provide the experimental results to demonstrate the effectiveness of our proposed method FVC on four benchmark datasets HEVC [27], UVG [24], VTL [1] and MCLJCV [34].”