BUILD-A-VOLCAP : AUTOMATED SYNTHETIC VALIDATION OF REAL-WORLD VOLUMETRIC CAPTURE QUALITY

Antonella Rech, Giulia Martinelli, Nicola Garau, Nicola Conci, Francesco G. B. De Natale

Abstract:

Volumetric capture techniques have significantly advanced in
recent years, enabling detailed 3D reconstructions of dynamic
real-world scenes. However, predicting their performance
prior to real-world deployment remains challenging, often
leading to costly experimental setups and uncertain outcomes.
In this paper, we present Build-A-Volcap, an automated synthetic validation environment designed to predict the quality
of real-world volumetric capture systems. Our solution constructs comprehensive synthetic datasets and environments
that faithfully simulate practical capture conditions. This
enables rigorous testing and benchmarking of volumetric
methods such as photogrammetry, NeRF, Gaussian Splatting and Radiant Foam without the need for physical setups.
Through extensive experiments, we demonstrate how BuildA-Volcap effectively identifies methodological strengths and
limitations, significantly reducing the synthetic-to-real gap.
Our pipeline enables researchers and companies to optimize
and validate their volumetric capture setups virtually, ensuring robust performance upon real-world deployment. More
information and code release on our project page: https:
//mmlab-cv.github.io/Build-A-Volcap/.