Millimetric Human Surface Capture in Minutes

Diego Thomas, Edmond Boyer, Jean-Sébastien Franco, Briac Toussaint

Abstract:

Detailed human surface capture from multiple images is an essential component
for many 3D production, analysis and transmission tasks. Yet producing
millimetric precision 3D models in practical time, and actually verifying
their 3D accuracy in a real-world capture context, remain key challenges
due to the lack of specific methods and data for these goals. We propose two
complementary contributions to this end. The first one is a highly scalable
neural surface radiance field approach able to achieve millimetric precision
by construction, while demonstrating high compute and memory efficiency.
The second one is a novel dataset of clothed mannequin geometry captured
with a high resolution hand-held 3D scanner paired with calibrated multiview
images, that allow to verify the millimetric accuracy claim. Although
our approach can produce such a highly dense and precise geometry, we
show how aggressive sparsification and optimizations of the neural surface
pipeline lead to estimations requiring only minutes of computation time and
a few GB of VRAM memory on GPU, while allowing for real-time millisecond
neural rendering. On the basis of our framework and dataset, we provide
a thorough experimental analysis of how such accuracies and efficiencies
are achieved in the context of multi-camera human acquisition.