[IPOL announce] new article: Accelerating NeRF with the Visual Hull

[announcements about the IPOL journal]

A new article is available in IPOL: https://www.ipol.im/pub/art/2024/553/

Roger Marí,
Accelerating NeRF with the Visual Hull,
Image Processing On Line, 14 (2024), pp. 217–231.
https://doi.org/10.5201/ipol.2024.553

Abstract
Neural rendering methods for learning the appearance and geometry of 3D 
scenes have gained tremendous popularity since 2020. In this field, NeRF 
or Neural Radiance Fields is the best-known methodology. Given a 
collection of multi-view images and their camera models, NeRF optimizes 
a neural network to learn the color and scene geometry that render the 
input images according to classical volumetric rendering techniques. 
NeRF operates in a self-supervised manner and provides a remarkable 
level of detail, but the time-consuming optimization process remains a 
major limitation. This paper reviews the Voxel-Accelerated NeRF 
(VaxNeRF), a simple acceleration strategy for NeRF proposed in 2021. 
VaxNeRF reduces the number of point queries required in training and 
inference time by considering only the region of space corresponding to 
the visual hull, i.e., the maximum volume compatible with the object 
silhouettes given by the multi-view collection. VaxNeRF requires only 
coarse foreground-background segmentation masks and minimal changes to 
the original NeRF code to improve speed by a factor of 2-8, without any 
performance degradation.