Home

Awesome

#DeepI2P: Image-to-Point Cloud Registration via Deep Classification

Summary

Video

PyTorch implementation for our CVPR 2021 paper DeepI2P. DeepI2P solves the problem of cross modality registration, i.e, solve the relative rotation R and translation t between the camera and the lidar.

DeepI2P: Image-to-Point Cloud Registration via Deep Classification<br> Jiaxin Li <sup>1</sup>, Gim Hee Lee <sup>2</sup> <br> <sup>1</sup>ByteDance, <sup>2</sup>National University of Singapore

Method

The intuition is to perform the Inverse Camera Projection, as shown in the images below. overview_1 overview_2

Repo Structure

Dataset and Models