PeRFception: Perception using Radiance Fields
This work addresses the need for efficient 3D data representation in computer vision, though it is incremental as it builds on existing NeRF methods.
The authors tackled the problem of using Neural Radiance Fields (NeRFs) for perception tasks by creating the first large-scale implicit representation dataset, PeRFception, which achieves a 96.4% memory compression rate and includes object-centric and scene-centric scans for classification and segmentation.
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 https://postech-cvlab.github.io/PeRFception .