Mobilenerf: Exploiting the polygon rasterization pipeline for efficient neural field rendering on mobile architectures

Z Chen, T Funkhouser, P Hedman… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Neural Radiance Fields (NeRFs) have demonstrated amazing ability to synthesize
images of 3D scenes from novel views. However, they rely upon specialized volumetric …

Neural radiance fields in the industrial and robotics domain: applications, research opportunities and use cases

E Šlapak, E Pardo, M Dopiriak, T Maksymyuk… - Robotics and Computer …, 2024 - Elsevier
The proliferation of technologies, such as extended reality (XR), has increased the demand
for high-quality three-dimensional (3D) graphical representations. Industrial 3D applications …

Learning a more continuous zero level set in unsigned distance fields through level set projection

J Zhou, B Ma, S Li, YS Liu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Latest methods represent shapes with open surfaces using unsigned distance functions
(UDFs). They train neural networks to learn UDFs and reconstruct surfaces with the …

Sparsepose: Sparse-view camera pose regression and refinement

S Sinha, JY Zhang, A Tagliasacchi… - Proceedings of the …, 2023 - openaccess.thecvf.com
Camera pose estimation is a key step in standard 3D reconstruction pipelines that operates
on a dense set of images of a single object or scene. However, methods for pose estimation …

Gridpull: Towards scalability in learning implicit representations from 3d point clouds

C Chen, YS Liu, Z Han - Proceedings of the ieee/cvf …, 2023 - openaccess.thecvf.com
Learning implicit representations has been a widely used solution for surface reconstruction
from 3D point clouds. The latest methods infer a distance or occupancy field by overfitting a …

Canonical factors for hybrid neural fields

B Yi, W Zeng, S Buchanan… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Factored feature volumes offer a simple way to build more compact, efficient, and
intepretable neural fields, but also introduce biases that are not necessarily beneficial for …

DReg-NeRF: Deep registration for neural radiance fields

Y Chen, GH Lee - … of the IEEE/CVF International Conference …, 2023 - openaccess.thecvf.com
Abstract Although Neural Radiance Fields (NeRF) is popular in the computer vision
community recently, registering multiple NeRFs has yet to gain much attention. Unlike the …

Soac: Spatio-temporal overlap-aware multi-sensor calibration using neural radiance fields

Q Herau, N Piasco, M Bennehar… - Proceedings of the …, 2024 - openaccess.thecvf.com
In rapidly-evolving domains such as autonomous driving the use of multiple sensors with
different modalities is crucial to ensure high operational precision and stability. To correctly …

Benchmarking Neural Radiance Fields for Autonomous Robots: An Overview

Y Ming, X Yang, W Wang, Z Chen, J Feng… - arXiv preprint arXiv …, 2024 - arxiv.org
Neural Radiance Fields (NeRF) have emerged as a powerful paradigm for 3D scene
representation, offering high-fidelity renderings and reconstructions from a set of sparse and …

[HTML][HTML] MARF: The medial atom ray field object representation

PB Sundt, T Theoharis - Computers & Graphics, 2023 - Elsevier
Abstract We propose Medial Atom Ray Fields (MARFs), a novel neural object representation
that enables accurate differentiable surface rendering with a single network evaluation per …