Learning-based ray sampling strategy for computation efficient neural radiance field generation

Yuqi Han; Jinli Suo; Qionghao Dai

doi:10.1117/12.2643835

4 January 2023 Learning-based ray sampling strategy for computation efficient neural radiance field generation

Yuqi Han, Jinli Suo, Qionghao Dai

Proceedings Volume 12317, Optoelectronic Imaging and Multimedia Technology IX; 123170G (2023) https://doi.org/10.1117/12.2643835
Event: SPIE/COS Photonics Asia, 2022, Online Only

Abstract

The neural radiance field (NeRF) constructs an implicit representation function to substitute the traditional 3D representation, such as point cloud, mesh, and voxels, leading to consistent and efficient image rendering at desired observing spatial position. However, NeRF requires dense sampling in 3D space to build the continuous representation function. The huge amount of sampling points occupies intensive computing resources, which hinders NeRF from being integrated into the lightweight system. In this paper, we present a learning-based sampling strategy, which conducts dense sampling in regions with rich texture and sparse sampling in other regions, extremely reducing the computation resources and accelerating the learning speed. Furthermore, to alleviate the additional computation overhead caused by the proposed sampling strategy, we present a distributed structure to conduct the sampling decision individually. The distributed design releases the computation burden on the devices, which enables the deployment of the proposed strategy to the practical systems.

Conference Presentation

Citation Download Citation

Yuqi Han, Jinli Suo, and Qionghao Dai "Learning-based ray sampling strategy for computation efficient neural radiance field generation", Proc. SPIE 12317, Optoelectronic Imaging and Multimedia Technology IX, 123170G (4 January 2023); https://doi.org/10.1117/12.2643835

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available