As 3D point clouds become central to immersive media and capture pipelines, we need dependable ways to measure their perceptual visual quality. I took part in the ICIP 2023 Point Cloud Visual Quality Assessment Grand Challenge, a community effort to advance and benchmark methods for exactly this.

Point clouds are distorted in ways that differ sharply from 2D images (through compression, sampling, and reconstruction artifacts), and human perception of these distortions does not follow simple geometric error metrics. Assessing quality in a way that tracks what viewers actually notice is genuinely hard.

A grand challenge format brings the community together around shared data and evaluation, letting different approaches be compared on common ground. Contributing alongside a broad group of researchers offered a valuable view of where perceptual point-cloud quality assessment currently stands.

Efforts like this help push the field toward metrics that align with human perception, which is essential as point-cloud content moves into everyday applications. This was a collaborative effort with A. Chetouani, G. Valenzise, A. Ak, E. Zerman, M. Quach, M. Tliba, and others.

Part of the ICIP 2023 Grand Challenge; see my Publications page.

See the paper for the full methodology and results.