ICIP 2023 Point Cloud Visual Quality Assessment Grand Challenge Call for Papers

ICIP 2023 – Point Cloud Visual Quality Assessment Grand Challenge

https://sites.google.com/view/icip2023-pcvqa-grand-challenge/

 

Description: 

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.

 

Tracks:

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. 

 

Challenge Website:

Check the website for details about the tracks, the submission and
evaluation criteria:

https://sites.google.com/view/icip2023-pcvqa-grand-challenge/

 

 

Important Dates:

-       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

 

Organizing Committee:

-       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
--