The reviewed record of science sign in
Pith

arxiv: 2306.07087 · v1 · pith:XKWXOGVM · submitted 2023-06-12 · cs.CV · cs.RO

MaskedFusion360: Reconstruct LiDAR Data by Querying Camera Features

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:XKWXOGVMrecord.jsonopen to challenge →

classification cs.CV cs.RO
keywords lidardatacamerafeaturesfuseapplicationsdensemasked
0
0 comments X
read the original abstract

In self-driving applications, LiDAR data provides accurate information about distances in 3D but lacks the semantic richness of camera data. Therefore, state-of-the-art methods for perception in urban scenes fuse data from both sensor types. In this work, we introduce a novel self-supervised method to fuse LiDAR and camera data for self-driving applications. We build upon masked autoencoders (MAEs) and train deep learning models to reconstruct masked LiDAR data from fused LiDAR and camera features. In contrast to related methods that use birds-eye-view representations, we fuse features from dense spherical LiDAR projections and features from fish-eye camera crops with a similar field of view. Therefore, we reduce the learned spatial transformations to moderate perspective transformations and do not require additional modules to generate dense LiDAR representations. Code is available at: https://github.com/KIT-MRT/masked-fusion-360

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.