BVI-SynTex - A Synthetic Video Texture Dataset for Video Compression and Quality Assessment

Angeliki Katsenou

University of Bristol

Goce Dimitrov

University of Bristol

Di Ma

University of Bristol

David R. Bull

University of Bristol


Highly textured video content is challenging to compress since the bit-rate to video quality trade-off is high and complex perceptual masking influences performance. Test datasets that cover a wide range of texture types are thus important for codec evaluation, but few exist. In order to study the properties of video texture, this paper introduces a Synthetic video Texture dataset (BVI-SynTex) that was generated using a Computer-Generated Imagery (CGI) environment. It contains 196 sequences clustered in three different texture types and offers the capability of being able to generate many versions of the same scene with different video parameters. It therefore provides a flexible basis for studying the influence of texture type and parameters on video compression and perceived video quality. A thorough validation and comparison of BVI-SynTex with similarly textured natural video content is performed. The comparisons show that BVI-SynTex exhibits a comparable coverage over the spatial and temporal domain and that it produces similar encoding statistics to real video datasets. A subset of the BVI-SynTex dataset was selected to perform a subjective evaluation of compression using the HEVC codec. The results show the impact of the content parameters to both the compression efficiency and the perceived quality. The publicly available BVI-SynTex dataset contains all source sequences, the objective and subjective analysis results, providing a valuable resource for the research community.

The collection of papers below provides all related research results.

Leverhulme Trust


Examples of Synthetic and Real Video Textures


  • Papers
    • A. V. Katsenou, G. Dimitrov, D. Ma, and D. R. Bull, "BVI-SynTex - A Synthetic Video Texture Dataset for Video Compression and Quality Assessment", 2021 IEEE Transactions on Multimedia. [Paper]
    • D. Ma, A. V. Katsenou, and D. R. Bull, "A Synthetic Video Dataset for Video Compression Evaluation," 2019 IEEE International Conference in Image Processing. [Paper]
  • Datasets