ICIP 2023 – Point Cloud Visual Quality Assessment Grand Challenge
Point clouds are widely used in various applications, including virtual and mixed reality, construction, and autonomous driving. In recent years, point cloud processing, particularly coding and transmission, has gained increasing attention, resulting in new standardization activities such as MPEG G-PCC and V-PCC or JPEG Pleno. Recent point cloud compression approaches use deep neural networks for efficient coding of point clouds. However, lossy compression, transmission, or processing can lead to visual distortion, which calls for effective methods to quantify the quality of processed point clouds.
This challenge aims to evaluate the performance of PC quality metrics on a new dataset, which includes 75 pristine point clouds compressed with different algorithms. The goal is to benchmark the effectiveness of the proposed methods and compare them with state-of-the-art approaches.
The ICIP 2023 PCVQA Challenge consists of 5 tracks. The tracks correspond to different use cases in which quality metrics are typically used:
(1) Full-reference, broad-range quality estimation: This track aims to assess the perceptual fidelity of distorted contents with respect to the originals for any level of distortion. This is the most generic and traditional set-up for quality metrics.
(2) No-reference, broad-range quality estimation: This track is similar to Track (1) but the proposed metrics do not have access to the original content.
(3) Full-reference, high-quality range: This track focuses on metrics for high-end quality. These are desirable in applications such as content production, high-quality streaming, digital twins, etc.
(4) No-reference, high-quality range: This track is similar to Track (3), but metrics can use only processed point clouds without the originals.
(5) Intra-reference: The metrics should be sensible to quality differences within different processed versions of the same point cloud content. Metrics in this track are especially suitable to optimization scenarios, e.g., for point cloud compression and enhancement, and more in general as loss functions in end-to-end PC learning pipelines.
Each team can participate to one or more tracks.
Check the website for details about the tracks, the submission and evaluation criteria:
- Dataset available (in Codalab): February 18, 2023
- Deadline for model submission: March 25, 2023
- Final evaluation results: April 10, 2023
- Announcement of the results: April 17, 2023
- Deadline to submit a challenge paper to ICIP: April 26, 2023
- Aladine Chetouani, University of Orléans, France
- Ali Ak, University of Nantes, France
- Emin Zerman, Mid Sweden University, Sweden
- Marouane Tliba, University of Orléans, France
- Mohamed Amine Kerkouri, University of Orléans, France
- Giuseppe Valenzise, University Paris-Saclay, CNRS, France
- Maurice Quach, University Paris-Saclay, CNRS, France
- Patrick Le Callet, University of Nantes, France
Chargé de Recherche CNRS
Head of the Multimedia and Networking team
Laboratoire des Signaux et Systèmes (L2S, UMR 8506)
CNRS - CentraleSupelec - Université Paris-Saclay
3, rue Joliot Curie
91192 Gif-sur-Yvette Cedex, FRANCE
email: [log in to unmask]
tel: +33 1 69 85 17 72
“Immersive Video Technologies”
[log in to unmask]
If you don't already have a password for the LISTSERV.ACM.ORG server, we recommend
that you create one now. A LISTSERV password is linked to your email
address and can be used to access the web interface and all the lists to
which you are subscribed on the LISTSERV.ACM.ORG server.
To create a password, visit:
Once you have created a password, you can log in and view or change your
subscription settings at: