BASICS DATASET: Broad Quality Assessment of Static Point Clouds in a Compression Scenario
收藏资源简介：
Point clouds have become increasingly prevalent in representing 3D scenes within virtual environments, alongside 3D meshes. Their ease of capture has facilitated a wide array of applications on mobile devices, including smartphones and other microcontrollers. Notably, point cloud compression has reached an advanced stage and being standardized. However, the availability of quality assessment datasets, which are essential for the development of improved objective quality metrics, remains limited. We introduce BASICS, a large-scale quality assessment dataset tailored for static point clouds. The BASICS dataset comprises 75 unique point clouds, each compressed with four different algorithms, resulting in the evaluation of nearly 1500 point clouds by 3500 unique participants. For a detailed explanation of the dataset and the analysis done, please refer to the related publication: A. Ak, E. Zerman, M. Quach, A. Chetouani, A. Smolic, G. Valenzise, P. Le Callet, "BASICS: Broad quality Assessment of Static point clouds In Compression Scenarios", arXiv cs.MM 2302.04796. https://doi.org/10.48550/arXiv.2302.04796 BASICS paper is accepted to be published in IEEE TMM. The above article will be updated later on with the correct DOI. The BASICS dataset was previously used for the ICIP 2023 ICIP PCQVA Grand Challenge. Since the challenge is over, we are making it public for the community to build upon! Check the link below for the ICIP 2023 PCQVA Challenge Page: https://sites.google.com/view/icip2023-pcvqa-grand-challenge/
点云（Point Clouds）与三维网格（3D Meshes）一同，在虚拟环境的三维场景表征中愈发普及。其易于采集的特性推动了其在移动设备（涵盖智能手机与其他微控制器）上的多元应用。值得关注的是，点云压缩技术已发展至成熟阶段，并处于标准化进程之中。然而，支撑优化客观质量指标研发所必需的质量评估数据集，其可用资源仍较为稀缺。为此我们推出BASICS——一款专为静态点云打造的大规模质量评估数据集。该数据集包含75组独立点云，每组均通过四种不同的压缩算法进行处理，最终由3500名不同受试者完成了近1500组点云的质量评估工作。如需了解该数据集与相关分析的详细内容，请参阅以下发表成果：A. Ak、E. Zerman、M. Quach、A. Chetouani、A. Smolic、G. Valenzise、P. Le Callet，《BASICS：压缩场景下静态点云的全方位质量评估》，arXiv cs.MM 2302.04796，https://doi.org/10.48550/arXiv.2302.04796。BASICS相关论文已被IEEE TMM录用并将正式发表，后续将更新该论文的正式DOI编号。该数据集此前曾用于2023年国际图像处理会议（International Conference on Image Processing，ICIP）PCQVA大型挑战赛，鉴于该挑战赛已圆满落幕，我们现将该数据集公开，以供学界同仁开展后续研究工作！如需查看2023年ICIP PCQVA挑战赛页面，请访问以下链接：https://sites.google.com/view/icip2023-pcvqa-grand-challenge/
