Learning to Drop Points for LiDAR Scan Synthesis

@article{Nakashima2021LearningTD,
  title={Learning to Drop Points for LiDAR Scan Synthesis},
  author={Kazuto Nakashima and Ryo Kurazume},
  journal={2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year={2021},
  pages={222-229}
}
  • Kazuto Nakashima, R. Kurazume
  • Published 23 February 2021
  • Computer Science, Environmental Science
  • 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
3D laser scanning by LiDAR sensors plays an important role for mobile robots to understand their surroundings. Nevertheless, not all systems have high resolution and accuracy due to hardware limitations, weather conditions, and so on. Generative modeling of LiDAR data as scene priors is one of the promising solutions to compensate for unreliable or incomplete observations. In this paper, we propose a novel generative model for learning LiDAR data based on generative adversarial networks. As in… 

Figures and Tables from this paper

Learning to Simulate Realistic LiDARs

TLDR
A model that learns a mapping between RGB images and corresponding LiDAR features such as raydrop or per- point intensities directly from real datasets is proposed, and it is shown that this model can learn to encode realistic effects such as dropped points on transparent surfaces or high intensity returns on reflective materials.

Learning to Generate Realistic LiDAR Point Clouds

. We present LiDARGen, a novel, effective, and controllable generative model that produces realistic LiDAR point cloud sensory readings. Our method leverages the powerful score-matching energy-based

3D Object Detection for Autonomous Driving: A Review and New Outlooks

TLDR
This paper conducts a comprehensive survey of the progress in 3D object detection from the aspects of models and sensory inputs, including LiDAR-based, camera- based, and multi-modal detection approaches, and provides an in-depth analysis of the potentials and challenges in each category of methods.

SoK: On the Semantic AI Security in Autonomous Driving

TLDR
This paper takes the initiative to develop an open-source, uniform, and extensible system-driven evaluation platform, named PASS, for the semantic AD AI security research community, and uses the implemented platform prototype to showcase the capabilities and benefits of such a platform using representative semantic ADAI attacks.

A Survey on Deep Domain Adaptation for LiDAR Perception

TLDR
A comprehensive review of recent progress in domain adaptation methods is presented and interesting research questions specifically targeted towards LiDAR perception are formulates.

References

SHOWING 1-10 OF 30 REFERENCES

Deep Generative Modeling of LiDAR Data

TLDR
This work shows that one can adapt deep generative models for this task by unravelling lidar scans into a 2D point map, and proposes a novel data representation that augments the 2D signal with absolute positional information.

Progressive Growing of GANs for Improved Quality, Stability, and Variation

TLDR
A new training methodology for generative adversarial networks is described, starting from a low resolution, and adding new layers that model increasingly fine details as training progresses, allowing for images of unprecedented quality.

Analyzing and Improving the Image Quality of StyleGAN

TLDR
This work redesigns the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images, and thereby redefines the state of the art in unconditional image modeling.

Noise Robust Generative Adversarial Networks

  • Takuhiro KanekoT. Harada
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
TLDR
Noise robust GANs are proposed, which can learn a clean image generator even when training images are noisy, and the applicability of NR-GANs in image denoising is shown, which demonstrates the effectiveness of the network in noise robust image generation.

AmbientGAN: Generative models from lossy measurements

TLDR
This work considers the task of learning an implicit generative model given only lossy measurements of samples from the distribution of interest, and proposes a new method of training Generative Adversarial Networks (GANs) which is called AmbientGAN.

Categorical Reparameterization with Gumbel-Softmax

TLDR
It is shown that the Gumbel-Softmax estimator outperforms state-of-the-art gradient estimators on structured output prediction and unsupervised generative modeling tasks with categorical latent variables, and enables large speedups on semi-supervised classification.

The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables

TLDR
Concrete random variables---continuous relaxations of discrete random variables is a new family of distributions with closed form densities and a simple reparameterization, and the effectiveness of Concrete relaxations on density estimation and structured prediction tasks using neural networks is demonstrated.

Adam: A Method for Stochastic Optimization

TLDR
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.

Vision meets robotics: The KITTI dataset

TLDR
A novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research, using a variety of sensor modalities such as high-resolution color and grayscale stereo cameras and a high-precision GPS/IMU inertial navigation system.

Fukuoka datasets for place categorization

TLDR
Several multi-modal 3D datasets for the problem of categorization of places are presented, taken in different indoor and outdoor environments in Fukuoka city, Japan.