A Caltech Library Service

PeRFception: Perception using Radiance Fields

Jeong, Yoonwoo and Shin, Seungjoo and Lee, Junha and Choy, Christopher and Anandkumar, Animashree and Cho, Minsu and Park, Jaesik (2022) PeRFception: Perception using Radiance Fields. . (Unpublished)

[img] PDF - Submitted Version
Creative Commons Attribution Share Alike.


Use this Persistent URL to link to this item:


The recent progress in implicit 3D representation, i.e., Neural Radiance Fields (NeRFs), has made accurate and photorealistic 3D reconstruction possible in a differentiable manner. This new representation can effectively convey the information of hundreds of high-resolution images in one compact format and allows photorealistic synthesis of novel views. In this work, using the variant of NeRF called Plenoxels, we create the first large-scale implicit representation datasets for perception tasks, called the PeRFception, which consists of two parts that incorporate both object-centric and scene-centric scans for classification and segmentation. It shows a significant memory compression rate (96.4\%) from the original dataset, while containing both 2D and 3D information in a unified form. We construct the classification and segmentation models that directly take as input this implicit format and also propose a novel augmentation technique to avoid overfitting on backgrounds of images. The code and data are publicly available in

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper
Lee, Junha0000-0002-6821-2910
Choy, Christopher0000-0002-6566-3193
Anandkumar, Animashree0000-0002-6974-6797
Cho, Minsu0000-0001-7030-1958
Park, Jaesik0000-0003-0203-5138
Additional Information:Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
Record Number:CaltechAUTHORS:20221221-004646749
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:118542
Deposited By: George Porter
Deposited On:22 Dec 2022 20:37
Last Modified:22 Dec 2022 20:37

Repository Staff Only: item control page