Timezone: »

 
Poster
PeRFception: Perception using Radiance Fields
Yoonwoo Jeong · Seungjoo Shin · Junha Lee · Chris Choy · Anima Anandkumar · Minsu Cho · Jaesik Park

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #1025
in Poster Session 5 »

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 radiance fields 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 this radiance fields format as input and also propose a novel augmentation technique to avoid overfitting on backgrounds of images. The code and data are publicly available in "https://postech-cvlab.github.io/PeRFception/".

Keywords: image classification · neural radiance field · dataset · 3D semantic segmentation · 3D shape classification
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Yoonwoo Jeong (POSTECH)
Seungjoo Shin (POSTECH)
Junha Lee (POSTECH)
Chris Choy (Stanford University)
Anima Anandkumar (NVIDIA / Caltech)
Minsu Cho (POSTECH)
Jaesik Park (POSTECH)

More from the Same Authors