Publications / 2022

CVPR 2022 (Oral)

LiDAR Snowfall Simulation for Robust 3D Object Detection

Martin Hahner, Christos Sakaridis, Mario Bijelic, Felix Heide, Fisher Yu, Dengxin Dai and Luc Van Gool

Pipeline Overview

Animation of the LiDAR snowfall simulation pipeline

Theory

Interaction of a LiDAR beam with snowflakes Wet road surface model

Qualitative Results

Qualitative 3D object detection results in simulated snowfall

Downloads

  • snowflakes.zip 2.3 GB

    Precomputed snowflake patterns for the snowfall simulation.

    wget https://avi.ethz.ch/publications/2022/lidar_snow_simulation/snowflakes.zip
  • DROR.zip 215 MB

    Precomputed DROR point indices, an alternative to installing PCL.

    wget https://avi.ethz.ch/publications/2022/lidar_snow_simulation/DROR.zip
  • experiments.zip 265 MB

    Model checkpoints for inference on the STF dataset.

    wget https://avi.ethz.ch/publications/2022/lidar_snow_simulation/experiments.zip

Citation

@inproceedings{HahnerCVPR22,
  author    = {Hahner, Martin and Sakaridis, Christos and Bijelic, Mario and Heide, Felix and Yu, Fisher and Dai, Dengxin and Van Gool, Luc},
  title     = {{LiDAR Snowfall Simulation for Robust 3D Object Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year      = {2022},
}

This page was created by Martin Hahner. All rights reserved.