Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather

• URL: http://arxiv.org/abs/2407.02286v4
• Date: Wed, 17 Jul 2024 10:50:27 GMT
• Title: Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather
• Authors: Junsung Park, Kyungmin Kim, Hyunjung Shim,
• Abstract summary: Existing LiDAR semantic segmentation methods often struggle with performance declines in adverse weather conditions. Previous work has addressed this issue by simulating adverse weather or employing universal data augmentation during training. We propose new strategic data augmentation techniques to pinpoint the main causes of performance degradation. Our method achieves a notable 39.5 mIoU on the Semantic KITTI-to-SemanticSTF benchmark, improving the baseline by 8.1%p and establishing a new state-of-the-art.
• Score: 21.040167521248772
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Existing LiDAR semantic segmentation methods often struggle with performance declines in adverse weather conditions. Previous work has addressed this issue by simulating adverse weather or employing universal data augmentation during training. However, these methods lack a detailed analysis and understanding of how adverse weather negatively affects LiDAR semantic segmentation performance. Motivated by this issue, we identified key factors of adverse weather and conducted a toy experiment to pinpoint the main causes of performance degradation: (1) Geometric perturbation due to refraction caused by fog or droplets in the air and (2) Point drop due to energy absorption and occlusions. Based on these findings, we propose new strategic data augmentation techniques. First, we introduced a Selective Jittering (SJ) that jitters points in the random range of depth (or angle) to mimic geometric perturbation. Additionally, we developed a Learnable Point Drop (LPD) to learn vulnerable erase patterns with a Deep Q-Learning Network to approximate the point drop phenomenon from adverse weather conditions. Without precise weather simulation, these techniques strengthen the LiDAR semantic segmentation model by exposing it to vulnerable conditions identified by our data-centric analysis. Experimental results confirmed the suitability of the proposed data augmentation methods for enhancing robustness against adverse weather conditions. Our method achieves a notable 39.5 mIoU on the SemanticKITTI-to-SemanticSTF benchmark, improving the baseline by 8.1\%p and establishing a new state-of-the-art. Our code will be released at \url{https://github.com/engineerJPark/LiDARWeather}.

Related papers

• SemiDDM-Weather: A Semi-supervised Learning Framework for All-in-one Adverse Weather Removal [57.52777076116241]
  Adverse weather removal aims to restore clear vision under adverse weather conditions. This paper presents a pioneering semi-supervised all-in-one adverse weather removal framework built on the teacher-student network.
  arXiv  Detail & Related papers  (2024-09-29T12:12:22Z)
• Label-Efficient Semantic Segmentation of LiDAR Point Clouds in Adverse Weather Conditions [10.306226508237348]
  Adverse weather conditions can severely affect the performance of LiDAR sensors. Current approaches for detecting adverse weather points require large amounts of labeled data. This paper proposes a label-efficient approach to segment LiDAR point clouds in adverse weather.
  arXiv  Detail & Related papers  (2024-06-14T10:29:00Z)
• Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal [53.15046196592023]
  We introduce test-time adaptation into adverse weather removal in videos. We propose the first framework that integrates test-time adaptation into the iterative diffusion reverse process.
  arXiv  Detail & Related papers  (2024-03-12T14:21:30Z)
• WeatherProof: A Paired-Dataset Approach to Semantic Segmentation in Adverse Weather [9.619700283574533]
  We introduce a general paired-training method that leads to improved performance on images in adverse weather conditions. We create the first semantic segmentation dataset with accurate clear and adverse weather image pairs. We find that training on these paired clear and adverse weather frames which share an underlying scene results in improved performance on adverse weather data.
  arXiv  Detail & Related papers  (2023-12-15T04:57:54Z)
• Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
  We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies. Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
  arXiv  Detail & Related papers  (2023-11-30T08:22:08Z)
• Exploring the Application of Large-scale Pre-trained Models on Adverse Weather Removal [97.53040662243768]
  We propose a CLIP embedding module to make the network handle different weather conditions adaptively. This module integrates the sample specific weather prior extracted by CLIP image encoder together with the distribution specific information learned by a set of parameters.
  arXiv  Detail & Related papers  (2023-06-15T10:06:13Z)
• Energy-based Detection of Adverse Weather Effects in LiDAR Data [7.924836086640871]
  We propose a novel approach for detecting adverse weather effects in LiDAR data. Our method learns to associate low energy scores with inlier points and high energy scores with outliers. To help expand the research field of LiDAR perception in adverse weather, we release the SemanticSpray dataset.
  arXiv  Detail & Related papers  (2023-05-25T15:03:36Z)
• Robust 3D Object Detection in Cold Weather Conditions [7.924836086640871]
  Adverse weather conditions can negatively affect LiDAR-based object detectors. We focus on the phenomenon of vehicle gas exhaust condensation in cold weather conditions. We propose to solve this problem by using data augmentation and a novel training loss term.
  arXiv  Detail & Related papers  (2022-05-24T09:37:07Z)
• Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN [92.15895515035795]
  We describe an approach for supervising deep networks that are based on CycleGAN. We introduce new losses for training CycleGAN that lead to more effective training, resulting in high-quality reconstructions. We demonstrate that the proposed method can be effectively applied to different restoration tasks like de-raining, de-hazing and de-snowing.
  arXiv  Detail & Related papers  (2022-04-23T01:30:47Z)
• Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection [60.89616629421904]
  Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars. They are sensitive to adverse weather conditions such as rain, snow and fog due to reduced signal-to-noise ratio (SNR) and signal-to-background ratio (SBR)
  arXiv  Detail & Related papers  (2021-07-14T21:10:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.