Quant-NeRF: Efficient End-to-End Quantization of Neural Radiance Fields with Low-Precision 3D Gaussian Representation

Neural Radiance Field (NeRF) has been widely investigated for high-quality 3D object rendering based on captured 2D images. Previous research works have continuously improved the rendering quality with various sample representation and encoding strategies. However, a common bottleneck of NeRF is the...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 1 - 5
Main Authors: Hasssan, Ahmed, Anupreetham, Anupreetham, Meng, Jian, Seo, Jae-sun
Format: Conference Proceeding
Language:English
Published: IEEE 06.04.2025
Subjects:
3D Gaussian
Computational modeling
Encoding
Energy efficiency
Hardware
Hardware-aware algorithm
NeRF
Neural radiance field
Quantization (signal)
Quantized mean and co-variance
Rendering (computer graphics)
Signal processing algorithms
Speech processing
Three-dimensional displays
ISSN:2379-190X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural Radiance Field (NeRF) has been widely investigated for high-quality 3D object rendering based on captured 2D images. Previous research works have continuously improved the rendering quality with various sample representation and encoding strategies. However, a common bottleneck of NeRF is the extreme computational cost and the lack of compatibility with resource-constrained hardware. Despite the high fidelity of the rendered object, the extensive processing time of the pre-trained NeRF model largely degrades the feasibility of energy-efficient NeRF, especially for resource-constrained edge devices such as augmented/virtual reality (AR/VR) headsets. Most prior works focused on efficient hash table representation or simplified tensorial radiance fields with high-precision representation. However, the efficient, low precision, and hardware deployable NeRF with Gaussian-based modeling remains largely under-explored. Motivated by that, this paper proposes Quant-NeRF, a novel hardware-aware algorithm that performs 3D rendering with end-to-end low-precision representation and hardware deployable computation. Quant-NeRF achieves 60× acceleration compared to prior works on GPU, while maintaining high rendering quality as the full-precision baseline. The proposed algorithm achieves peak performance of 250 FPS.
ISSN:2379-190X
DOI:10.1109/ICASSP49660.2025.10889510