TY - GEN
T1 - Compressing Explicit Voxel Grid Representations
T2 - 23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023
AU - Deng, Chenxi Lola
AU - Tartaglione, Enzo
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023/1/1
Y1 - 2023/1/1
N2 - NeRFs have revolutionized the world of per-scene radiance field reconstruction because of their intrinsic compactness. One of the main limitations of NeRFs is their slow rendering speed, both at training and inference time. Recent research focuses on the optimization of an explicit voxel grid (EVG) that represents the scene, which can be paired with neural networks to learn radiance fields. This approach significantly enhances the speed both at train and inference time, but at the cost of large memory occupation. In this work we propose Re:NeRF, an approach that specifically targets EVG-NeRFs compressibility, aiming to reduce memory storage of NeRF models while maintaining comparable performance. We benchmark our approach with three different EVG-NeRF architectures on four popular benchmarks, showing Re:NeRF's broad usability and effectiveness.
AB - NeRFs have revolutionized the world of per-scene radiance field reconstruction because of their intrinsic compactness. One of the main limitations of NeRFs is their slow rendering speed, both at training and inference time. Recent research focuses on the optimization of an explicit voxel grid (EVG) that represents the scene, which can be paired with neural networks to learn radiance fields. This approach significantly enhances the speed both at train and inference time, but at the cost of large memory occupation. In this work we propose Re:NeRF, an approach that specifically targets EVG-NeRFs compressibility, aiming to reduce memory storage of NeRF models while maintaining comparable performance. We benchmark our approach with three different EVG-NeRF architectures on four popular benchmarks, showing Re:NeRF's broad usability and effectiveness.
KW - Algorithms: 3D computer vision
KW - Machine learning architectures
KW - and algorithms (including transfer, low-shot, semi-, self-, and un-supervised learning)
KW - formulations
U2 - 10.1109/WACV56688.2023.00129
DO - 10.1109/WACV56688.2023.00129
M3 - Conference contribution
AN - SCOPUS:85149040934
T3 - Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
SP - 1236
EP - 1245
BT - Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 3 January 2023 through 7 January 2023
ER -