paper-with-me

Papers Robust 3D Semantic Segmentation

“Robust 3D Semantic Segmentation” 태그가 달린 논문 20편 · 필터 해제

Data-Efficient Point Cloud Semantic Segmentation Pipeline for Unimproved Roads

2025-08-26 · Andrew Yarovoi, Christopher R. Valenta arxiv

In this case study, we present a data-efficient point cloud segmentation pipeline and training framework for robust segmentation of unimproved roads and seven other classes. Our method employs a two-stage training framew…

Robust 3D Semantic SegmentationPoint Cloud SegmentationPoint Clouds

Robo3D: Towards Robust and Reliable 3D Perception against Corruptions

2023-03-30 · ICCV 2023 1 · Lingdong Kong, Youquan Liu, Xin Li, Runnan Chen 외

The robustness of 3D perception systems under natural corruptions from environments and sensors is pivotal for safety-critical applications. Existing large-scale 3D perception datasets often contain data that are meticul…

3D Object Detection3D Semantic SegmentationRobust 3D Object DetectionRobust 3D Semantic Segmentation

Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation

2023-01-24 · ICCV 2023 1 · Gilles Puy, Alexandre Boulch, Renaud Marlet

Semantic segmentation of point clouds in autonomous driving datasets requires techniques that can process large numbers of points efficiently. Sparse 3D convolutions have become the de-facto tools to construct deep neura…

3D Semantic SegmentationAutonomous DrivingLIDAR Semantic SegmentationRobust 3D Semantic Segmentation+1

PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud

2022-11-28 · Tunhou Zhang, Mingyuan Ma, Feng Yan, Hai Li 외

The interaction and dimension of points are two important axes in designing point operators to serve hierarchical 3D models. Yet, these two axes are heterogeneous and challenging to fully explore. Existing works craft po…

Neural Architecture SearchRobust 3D Semantic SegmentationSemantic Segmentation

CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Driving

2022-07-26 · Hui-Xian Cheng, Xian-Feng Han, Guo-Qiang Xiao

Accurate and fast scene understanding is one of the challenging task for autonomous driving, which requires to take full advantage of LiDAR point clouds for semantic segmentation. In this paper, we present a \textbf{conc…

3D Semantic SegmentationAutonomous DrivingDescriptiveLIDAR Semantic Segmentation+4

2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds

2022-07-10 · Xu Yan, Jiantao Gao, Chaoda Zheng, Chao Zheng 외

As camera and LiDAR sensors capture complementary information used in autonomous driving, great efforts have been made to develop semantic segmentation algorithms through multi-modality data fusion. However, fusion-based…

3D Semantic SegmentationAutonomous DrivingKnowledge DistillationLIDAR Semantic Segmentation+3

GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation

2022-07-06 · Haibo Qiu, Baosheng Yu, DaCheng Tao

Point cloud semantic segmentation from projected views, such as range-view (RV) and bird's-eye-view (BEV), has been intensively investigated. Different views capture different information of point clouds and thus are com…

3D Semantic SegmentationLIDAR Semantic SegmentationRepresentation LearningRobust 3D Semantic Segmentation+2

CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation

2022-04-21 · Xiaoyan Li, Gang Zhang, Hongyu Pan, Zhenhua Wang

LiDAR semantic segmentation essential for advanced autonomous driving is required to be accurate, fast, and easy-deployed on mobile platforms. Previous point-based or sparse voxel-based methods are far away from real-tim…

Autonomous DrivingLIDAR Semantic SegmentationRobust 3D Semantic SegmentationSemantic Segmentation

Segment-Fusion: Hierarchical Context Fusion for Robust 3D Semantic Segmentation

2022-01-01 · CVPR 2022 1 · Anirud Thyagharajan, Benjamin Ummenhofer, Prashant Laddha, Om Ji Omer 외

3D semantic segmentation is a fundamental building block for several scene understanding applications such as autonomous driving, robotics and AR/VR. Several state-of-the-art semantic segmentation models suffer from …

3D Semantic SegmentationAutonomous DrivingInstance SegmentationRobust 3D Semantic Segmentation+3

FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding

2021-09-08 · Yiming Zhao, Lin Bai, Xinming Huang

Projecting the point cloud on the 2D spherical range image transforms the LiDAR semantic segmentation to a 2D segmentation task on the range image. However, the LiDAR range image is still naturally different from the reg…

3D Semantic SegmentationLIDAR Semantic SegmentationRobust 3D Semantic SegmentationSemantic Segmentation+1

RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation

2021-03-24 · ICCV 2021 10 · Jianyun Xu, Ruixiang Zhang, Jian Dou, Yushi Zhu 외

Point clouds can be represented in many forms (views), typically, point-based sets, voxel-based cells or range-based images(i.e., panoramic view). The point-based view is geometrically accurate, but it is disordered, whi…

Point Cloud SegmentationQuantizationRobust 3D Semantic Segmentation

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

2020-11-19 · CVPR 2021 1 · Xinge Zhu, Hui Zhou, Tai Wang, Fangzhou Hong 외

State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. Although this corporation shows the competitiveness in the po…

3D Semantic SegmentationLIDAR Semantic SegmentationPanoptic SegmentationRobust 3D Semantic Segmentation+2

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

2020-07-31 · ECCV 2020 8 · Haotian Tang, Zhijian Liu, Shengyu Zhao, Yujun Lin 외

Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely. Given the limited hardware resources, existing 3D perception models are not able to recognize small instances (e.g., ped…

3D Object Detection3D Semantic SegmentationLIDAR Semantic SegmentationNeural Architecture Search+4

PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation

2020-03-31 · CVPR 2020 6 · Yang Zhang, Zixiang Zhou, Philip David, Xiangyu Yue 외

The need for fine-grained perception in autonomous driving systems has resulted in recently increased research on online semantic segmentation of single-scan LiDAR. Despite the emerging datasets and technological advance…

3D Semantic SegmentationAutonomous DrivingLIDAR Semantic SegmentationRobust 3D Semantic Segmentation+2

SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving

2020-03-07 · Tiago Cortinhal, George Tzelepis, Eren Erdal Aksoy

In this paper, we introduce SalsaNext for the uncertainty-aware semantic segmentation of a full 3D LiDAR point cloud in real-time. SalsaNext is the next version of SalsaNet [1] which has an encoder-decoder architecture w…

3D Semantic SegmentationAutonomous DrivingDecoderRobust 3D Semantic Segmentation+1

RangeNet++: Fast and Accurate LiDAR Semantic Segmentation

2019-11-04 · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2019 11 · Andres Milioto, Ignacio Vizzo, Jens Behley, Cyrill Stachniss

Perception in autonomous vehicles is often carried out through a suite of different sensing modalities. Given the massive amount of openly available labeled RGB data and the advent of high-quality deep learning algorithm…

3D Semantic SegmentationAutonomous VehiclesGPULIDAR Semantic Segmentation+2

KPConv: Flexible and Deformable Convolution for Point Clouds

2019-04-18 · ICCV 2019 10 · Hugues Thomas, Charles R. Qi, Jean-Emmanuel Deschaud, Beatriz Marcotegui 외

We present Kernel Point Convolution (KPConv), a new design of point convolution, i.e. that operates on point clouds without any intermediate representation. The convolution weights of KPConv are located in Euclidean spac…

3D Part Segmentation3D Point Cloud Classification3D Semantic SegmentationDescriptive+4

4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks

2019-04-18 · CVPR 2019 6 · Christopher Choy, JunYoung Gwak, Silvio Savarese

In many robotics and VR/AR applications, 3D-videos are readily-available sources of input (a continuous sequence of depth images, or LIDAR scans). However, those 3D-videos are processed frame-by-frame either through 2D c…

3D Semantic Segmentation4D Spatio Temporal Semantic SegmentationRobust 3D Semantic SegmentationSemantic Segmentation

SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud

2018-09-22 · Bichen Wu, Xuanyu Zhou, Sicheng Zhao, Xiangyu Yue 외

Earlier work demonstrates the promise of deep-learning-based approaches for point cloud segmentation; however, these approaches need to be improved to be practically useful. To this end, we introduce a new model SqueezeS…

3D Semantic SegmentationDomain AdaptationPoint Cloud SegmentationRobust 3D Semantic Segmentation+3

SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud

2017-10-19 · Bichen Wu, Alvin Wan, Xiangyu Yue, Kurt Keutzer

In this paper, we address semantic segmentation of road-objects from 3D LiDAR point clouds. In particular, we wish to detect and categorize instances of interest, such as cars, pedestrians and cyclists. We formulate this…

3D Semantic SegmentationAutonomous DrivingClusteringRobust 3D Semantic Segmentation+1
1–20 / 20