Point clouds (PC) are widely used for storing and transmitting 3D visual data in applications like virtual reality, autonomous driving, etc. To deal with the large size and complexity of point clouds, efficient compression methods have been developed, including MPEG standards and recent deep-learning-based approaches. To optimize and benchmark processing algorithms and codecs, point cloud quality metrics are crucial. Several PC quality metrics have been proposed so far, but their ability to predict subjective opinion scores is still being assessed due to the lack of diverse datasets with subjective annotations. To address this, this grand challenge provides a large dataset of distorted (compressed) point clouds from different classes and codecs, with ground-truth subjective scores. Participants can test their algorithms on this dataset to benchmark against competitors and advance point cloud quality assessment. The results of the challenge will be published and the dataset will be made available to foster research in this domain.
Contributors to the challenge are invited to submit a challenge paper to ICIP 2023 (deadline: 26 April 2023). The best submissions will also have the chance to submit an extended version of their paper to a Special Issue that we will organize in Elsevier Signal Processing: Image Communication (details will be provided soon). Please visit the website often. Questions, please contact the Challenge team!
