NerfAcc: A General NeRF Acceleration Toolbox

10/10/2022
by   Ruilong Li, et al.
0

We propose NerfAcc, a toolbox for efficient volumetric rendering of radiance fields. We build on the techniques proposed in Instant-NGP, and extend these techniques to not only support bounded static scenes, but also for dynamic scenes and unbounded scenes. NerfAcc comes with a user-friendly Python API, and is ready for plug-and-play acceleration of most NeRFs. Various examples are provided to show how to use this toolbox. Code can be found here: https://github.com/KAIR-BAIR/nerfacc.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/15/2020

NeRF++: Analyzing and Improving Neural Radiance Fields

Neural Radiance Fields (NeRF) achieve impressive view synthesis results ...
research
01/01/2023

Detachable Novel Views Synthesis of Dynamic Scenes Using Distribution-Driven Neural Radiance Fields

Representing and synthesizing novel views in real-world dynamic scenes f...
research
04/13/2023

Representing Volumetric Videos as Dynamic MLP Maps

This paper introduces a novel representation of volumetric videos for re...
research
03/15/2023

RefiNeRF: Modelling dynamic neural radiance fields with inconsistent or missing camera parameters

Novel view synthesis (NVS) is a challenging task in computer vision that...
research
08/05/2023

feather – a Python SDK to share and deploy models

At its core, feather was a tool that allowed model developers to build s...
research
07/05/2022

Manipulator Differential Kinematics Part I: Kinematics, Velocity, and Applications

Manipulator kinematics is concerned with the motion of each link within ...
research
07/05/2022

Manipulator Differential Kinematics Part II: Acceleration and Advanced Applications

This is the second and final article on the tutorial on manipulator diff...

Please sign up or login with your details

Forgot password? Click here to reset