在自动驾驶之心平台的论文推荐专栏文章列表整理。
论文推荐专栏：紧跟自动驾驶感知的前沿论文，将前沿论文按照论文思路、主要贡献、网络设计、实验结果四个部分进行拆分，写成中文的文章，向广大中文研究者和自动驾驶之心的关注者提供前沿论文速览服务。
| 日期(Date) | 论文名称（Paper name) | 翻译名字 | 论文推荐链接 | 论文链接(paper link) | 代码链接(code link) |
|---|---|---|---|---|---|
| 2023-05-29 | Deep Radar Inverse Sensor Models for Dynamic Occupancy Grid Maps (Preprint)* | 用于动态占用网格地图的深度毫米波雷达逆传感器模型（Inverse Sensor Models） | https://zhuanlan.zhihu.com/p/632717882 | https://arxiv.org/pdf/2305.12409.pdf | |
| 2023-05-29 | Curricular Object Manipulation in LiDAR-based Object Detection | CVPR 2023 基于LiDAR的目标检测中的Curricular Object Manipulation | https://zhuanlan.zhihu.com/p/632927353 | https://arxiv.org/pdf/2304.04248.pdf | |
| 2023-05-27 | MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer | CVPR 2023 MonoATT:在线单目3D目标检测与自适应Token Transformer | https://zhuanlan.zhihu.com/p/632577292 | https://arxiv.org/pdf/2303.13018.pdf | |
| 2023-05-23 | PVO: Panoptic Visual Odometry | CVPR 2023 PVO：全景视觉里程计 | https://zhuanlan.zhihu.com/p/631643495 | (https://arxiv.org/pdf/2207.01610.pdf) | https://zju3dv.github.io/pvo/ |
| 2023-05-22 | Dense Distinct Query for End-to-End Object Detection | CVPR 2023 用于端到端目标检测的稠密Distinct Query | https://zhuanlan.zhihu.com/p/625613243 | https://arxiv.org/pdf/2303.12776.pdf | |
| 2023-05-21 | Referring Multi-Object Tracking | CVPR 2023 Referring多目标跟踪（旷视科技） | https://zhuanlan.zhihu.com/p/631012208 | https://arxiv.org/pdf/2303.03366.pdf | https://github.com/wudongming97/RMOT |
| 2023-05-15 | EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision | CVPR 2023 EFEM:基于等变神经场期望最大化的无场景监督三维目标分割 | https://zhuanlan.zhihu.com/p/628708768 | https://arxiv.org/pdf/2303.15440.pdf | |
| 2023-05-14 | 3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds | CVPR 2023 3D语义分割in the Wild: 学习不利条件点云的泛化模型 | https://zhuanlan.zhihu.com/p/628708057 | https://arxiv.org/pdf/2304.00690.pdf | https://github.com/xiaoaoran/SemanticSTF |
| 2023-05-14 | Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection | CVPR 2023 基于Hierarchical监督和Shuffle数据增强的半监督三维目标检测 | https://zhuanlan.zhihu.com/p/626264665 | https://arxiv.org/pdf/2304.01464.pdf | |
| 2023-05-13 | Exploiting the Complementarity of 2D and 3D Networks to Address Domain-Shift in 3D Semantic Segmentation | CVPR2023 利用2D和3D网络的互补性，解决三维语义分割中的域偏移问题 | https://zhuanlan.zhihu.com/p/628707262 | https://arxiv.org/pdf/2304.02991.pdf | |
| 2023-05-5 | MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving | CVPR 2023 MSeg3D:用于自动驾驶的多模态3D语义分割（浙江大学最新） | https://zhuanlan.zhihu.com/p/626843023 | https://arxiv.org/pdf/2303.08600.pdf | |
| 2023-05-5 | Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection | CVPR 2023 基于等级监督和Shuffle数据增强的半监督3D目标检测 | https://zhuanlan.zhihu.com/p/627095580 | https://arxiv.org/pdf/2304.01464.pdf | https://github.com/azhuantou/HSSDA |
| 2030-05-01 | Renderable Neural Radiance Map for Visual Navigation | CVPR 2023 用于视觉导航的可绘制神经辐射Map | https://zhuanlan.zhihu.com/p/626201215 | https://arxiv.org/pdf/2303.00304.pdf | |
| 2030-04-28 | MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection | CVPR 2023 Mix Teacher:半监督目标检测新方法 | https://zhuanlan.zhihu.com/p/625756689 | https://arxiv.org/pdf/2303.09061.pdf | |
| 2023-05-04 | Rotation-Invariant Transformer for Point Cloud Matching | CVPR 2023 用于点云匹配的旋转不变Transformer | https://zhuanlan.zhihu.com/p/624188832 | https://arxiv.org/pdf/2303.08231.pdf | |
| 2023-04-27 | ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completion | CVPR 2023 ACL-SPC：用于自监督点云补全的自适应Closed-Loop系统 | https://zhuanlan.zhihu.com/p/625456198 | https://arxiv.org/pdf/2303.01979.pdf | |
| 2032-04-25 | SCPNet: Semantic Scene Completion on Point Cloud | CVPR 2023 SCPNet：点云上的语义场景补全 | https://zhuanlan.zhihu.com/p/624187098 | https://arxiv.org/pdf/2303.06884.pdf | |
| 2023-04-24 | Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis | CVPR 2023 用于高效点云分析的稀疏卷积网络二值化 | https://zhuanlan.zhihu.com/p/623709104 | https://arxiv.org/pdf/2303.15493.pdf | |
| 2023-04-20 | PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection | CVPR 2023 PiMAE：用于3D目标检测的点云和图像交互式自动编码器 | https://zhuanlan.zhihu.com/p/623529429 | https://arxiv.org/pdf/2303.08129.pdf | |
| 2023-04-15 | 3D Video Object Detection with Learnable Object-Centric Global Optimization | CVPR 2023 基于可学习目标中心全局优化的3D视频目标检测 | https://zhuanlan.zhihu.com/p/621614451 | https://arxiv.org/pdf/2303.15416.pdf | https://github.com/jiaweihe1996/BA-Det |
| 2023-04-15 | LinK: Linear Kernel for LiDAR-based 3D Perception | CVPR 2023 LinK：基于lidar的3D感知的线性Kernel | https://zhuanlan.zhihu.com/p/622237858 | https://arxiv.org/pdf/2303.16094.pdf | |
| 2023-04-14 | Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View | CVPR 2023 面向鸟瞰多视图三维目标检测的域泛化 | https://zhuanlan.zhihu.com/p/620518090 | https://arxiv.org/pdf/2303.01686.pdf | |
| 2023-04-11 | NeuralPCI: Spatio-temporal Neural Field for 3D Point Cloud Multi-frame Non-linear Interpolation | CVPR 2023 基于时空神经辐射场的三维点云多帧非线性插值 | https://zhuanlan.zhihu.com/p/619200995 | https://arxiv.org/pdf/2303.15126.pdf | https://github.com/ispc-lab/NeuralPCI |
| 2023-04-12 | Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency | CVPR 2023 基于多视图投影和方向一致性的弱监督单目3D检测 | https://zhuanlan.zhihu.com/p/621462564 | https://arxiv.org/pdf/2303.08686.pdf | https://github.com/weakmono3d/weakmono3d |
| 2023-04-09 | TBP-Former: Learning Temporal Bird’s-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving | CVPR 2023 TBP-Former: 最新基于BEV的以视觉为中心的联合感知和预测网络 | https://zhuanlan.zhihu.com/p/620518461 | https://arxiv.org/pdf/2303.09998.pdf | https://github.com/MediaBrain-SJTU/TBP-Former |
| 2023-04-08 | SimpleNet: A Simple Network for Image Anomaly Detection and Localization | CVPR 2023 SimpleNet：一个简单的图像异常检测和定位网络 | https://zhuanlan.zhihu.com/p/619199955 | https://arxiv.org/pdf/2303.15140.pdf | https://github.com/DonaldRR/SimpleNet |
| 2023-04-06 | Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation | CVPR2023 Learning to Retain while Acquiring:对抗Adversarial Data-Free知识蒸馏中的分布偏移 | https://zhuanlan.zhihu.com/p/617924951 | https://arxiv.org/pdf/2302.14290.pdf | |
| 2023-04-03 | Viewpoint Equivariance for Multi-View 3D Object Detection | CVPR 2023 多视图3D目标检测中的viewpoint equivariance | https://zhuanlan.zhihu.com/p/619170916 | https://arxiv.org/pdf/2303.14548.pdf | https://github.com/TRI-ML/VEDet |
| 2023-03-29 | ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution | CVPR2023 ISBNet：一种基于实例感知采样和box感知动态卷积的三维点云实例分割网络 | https://zhuanlan.zhihu.com/p/617923193 | https://arxiv.org/pdf/2303.00246.pdf | |
| 2023-03-29 | Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision | CVPR2023 Hidden Gems: 使用跨模态监督的4D雷达场景流学习 | https://zhuanlan.zhihu.com/p/617733380 | https://arxiv.org/pdf/2303.00462.pdf | https://github.com/Toytiny/CMFlow |
| 2023-03-24 | Multimodal Industrial Anomaly Detection via Hybrid Fusion | CVPR 2023 多模态融合的工业异常检测 | https://zhuanlan.zhihu.com/p/615572115 | https://arxiv.org/pdf/2303.00601.pdf | https://github.com/nomewang/M3DM |
| 2023-03-22 | Token Contrast for Weakly-Supervised Semantic Segmentation | CVPR 2023 基于Token对比的弱监督语义分割 | https://zhuanlan.zhihu.com/p/615570599 | https://arxiv.org/pdf/2303.01267.pdf | https://github.com/rulixiang/ToCo |
| 2023-03-21 | Delivering Arbitrary-Modal Semantic Segmentation | CVPR 2023 提供任意模态语义分割 | https://zhuanlan.zhihu.com/p/615573285 | https://arxiv.org/pdf/2303.01480.pdf | https://jamycheung.github.io/DELIVER.html |
| 2023-03-14 | PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees | CVPR2023 PointCert: 一种鲁棒的点云分类网络 | https://zhuanlan.zhihu.com/p/614021909 | https://arxiv.org/pdf/2303.01959.pdf | |
| 2023-03-11 | MixVPR: Feature Mixing for Visual Place Recognition | MixVPR:用于视觉场所识别的特征混合 | https://zhuanlan.zhihu.com/p/613070820 | https://arxiv.org/pdf/2303.02190v1.pdf | |
| 2023-03-09 | BSH-Det3D: Improving 3D Object Detection with BEV Shape Heatmap | BSH-Det3D:改进三维目标检测与BEV shape heatmap | https://zhuanlan.zhihu.com/p/612497856 | https://arxiv.org/pdf/2303.02000.pdf | |
| 2023-03-05 | Efficient Context Integration through Factorized Pyramidal Learning for Ultra-Lightweight Semantic Segmentation | 基于分解金字塔学习的上下文集成用于超轻量级语义分割 | https://zhuanlan.zhihu.com/p/611424753 | https://arxiv.org/pdf/2302.11785.pdf | |
| 2023-02-22 | Uncertainty-Aware AB3DMOT by Variational 3D Object Detection | 变分三维目标检测的不确定性感知算法 | https://zhuanlan.zhihu.com/p/608180167 | https://arxiv.org/pdf/2302.05923.pdf | |
| 2023-02-19 | On the Adversarial Robustness of Camera-based 3D Object Detection | 基于camera的三维目标检测的对抗鲁棒性研究 | https://zhuanlan.zhihu.com/p/607565836 | https://arxiv.org/pdf/2301.10766.pdf | |
| 2023-02-17 | Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Driving | 自动驾驶激光雷达点云的Generalized Few-Shot三维目标检测 | https://zhuanlan.zhihu.com/p/607076049 | https://arxiv.org/pdf/2302.03914v1.pdf | |
| 2023-02-15 | Variational Voxel Pseudo Image Tracking | 变分voxel伪图像跟踪 | https://zhuanlan.zhihu.com/p/606685230 | https://arxiv.org/pdf/2302.05914v1.pdf | |
| 2023-02-12 | LiDAR-CS Dataset: LiDAR Point Cloud Dataset with Cross-Sensors for 3D Object Detection | LiDAR-CS Dataset：用于3D目标检测的跨传感器激光雷达点云数据集 | https://zhuanlan.zhihu.com/p/605624779 | https://arxiv.org/pdf/2301.12515v1.pdf | https://github.com/LiDAR-Perception/LiDAR-CS |
| 2023-02-10 | Generating Evidential BEV Maps in Continuous Driving Space | 连续驾驶空间中生成Evidential BEV Maps | https://zhuanlan.zhihu.com/p/605288916 | https://arxiv.org/pdf/2302.02928v1.pdf | |
| 2023-02-06 | Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss | 基于语义容忍对比损失的自监督图像到点云蒸馏(Distillation) | https://zhuanlan.zhihu.com/p/603993309 | https://arxiv.org/pdf/2301.05709v1.pdf | |
| 2023-02-04 | BIDIRECTIONAL PROPAGATION FOR CROSS-MODAL 3D OBJECT DETECTION | ICLR 2023 | 跨模态三维目标检测的双向传播 | https://zhuanlan.zhihu.com/p/603432375 | https://arxiv.org/pdf/2301.09077v1.pdf | https://github.com/Eaphan/BiProDet |
| 2023-2-02 | SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via Swin Transformer and Densely Cascaded Network | SwinDepth：基于Swin Transformer和密集级联网络的单目序列无监督深度估计 | https://zhuanlan.zhihu.com/p/602756208 | https://arxiv.org/pdf/2301.06715v1.pdf | |
| 2023-01-29 | SensorX2car: Sensors-to-car calibration for autonomous driving in road scenarios | SensorX2car:道路场景中自动驾驶的传感器到车体标定(calibration) | https://zhuanlan.zhihu.com/p/601700023 | https://arxiv.org/pdf/2301.07279.pdf | https://github.com/OpenCalib/SensorX2car |
| 2023-01-27 | PTA-Det: Point Transformer Associating Point cloud and Image for 3D Object Detection | PTA-Det：用于三维目标检测的点云与图像关联点Transformer | https://zhuanlan.zhihu.com/p/601157599 | https://arxiv.org/pdf/2301.07301.pdf | |
| 2023-01-25 | BSNet: Lane Detection via Draw B-spline Curves Nearby | BSNet：基于B-spline曲线的车道线检测 | https://zhuanlan.zhihu.com/p/600924538 | https://arxiv.org/pdf/2301.06910.pdf | |
| 2023-01-25 | OA-BEV: Bringing Object Awareness to Bird’s-Eye-View Representation for Multi-Camera 3D Object Detection | OA-BEV：将目标感知引入多摄像机3D目标检测的鸟瞰视图表示 | https://zhuanlan.zhihu.com/p/600909451 | https://arxiv.org/pdf/2301.05711.pdf | |
| 2023-01-22 | Object Detection in 3D Point Clouds via Local Correlation-Aware Point Embedding | 基于局部相关感知点嵌入的三维点云目标检测 | https://zhuanlan.zhihu.com/p/600492379 | https://arxiv.org/pdf/2301.04613v1.pdf | |
| 2023-01-22 | Street-View Image Generation from a Bird’s-Eye View Layout | 基于鸟瞰布局的街景图像生成 | https://zhuanlan.zhihu.com/p/600448216 | https://arxiv.org/pdf/2301.04634v1.pdf | |
| 2023-01-14 | POLICY PRE-TRAINING FOR AUTONOMOUS DRIVING VIA SELF-SUPERVISED GEOMETRIC MODELING | 基于自监督几何建模的自动驾驶策略预训练 | https://zhuanlan.zhihu.com/p/599014144 | https://arxiv.org/pdf/2301.01006.pdf | https://github.com/OpenDriveLab/PPGeo |
| 2023-01-13 | Super Sparse 3D Object Detection | 超稀疏三维目标检测 | https://zhuanlan.zhihu.com/p/598713876 | https://arxiv.org/pdf/2301.02562.pdf | https://github.com/tusen-ai/SST |
| 2023-01-12 | PanDepth: Joint Panoptic Segmentation and Depth Completion | PanDepth：联合全景分割与深度补全 | https://zhuanlan.zhihu.com/p/598488004 | https://arxiv.org/pdf/2212.14180v1.pdf | https://github.com/juanb09111/PanDepth |
| 2023-01-10 | Cross Modal Transformer: Towards Fast and Robust 3D Object Detection | 基于坐标编码的3D目标检测跨模态Transformer | https://zhuanlan.zhihu.com/p/597516255 | https://arxiv.org/pdf/2301.01283.pdf | https://github.com/junjie18/CMT |
| 2023-01-10 | An Integrated LiDAR-SLAM System for Complex Environment with Noisy Point Clouds | 一种用于含噪声点云复杂环境的集成LiDAR-SLAM系统 | https://zhuanlan.zhihu.com/p/597516768 | https://arxiv.org/pdf/2212.05705.pdf | |
| 2023-01-04 | CC-3DT: Panoramic 3D Object Tracking via Cross-Camera Fusion | CC-3DT:基于跨相机融合的全景三维目标跟踪 | https://zhuanlan.zhihu.com/p/596563671 | https://arxiv.org/pdf/2212.01247.pdf | https://www.vis.xyz/pub/cc-3dt/ |
| 2023-01-03 | Estimation of Appearance and Occupancy Information in Bird’s Eye View from Surround Monocular Images | 从环视单目图像估计鸟瞰视野中的外观和占用信息 | https://zhuanlan.zhihu.com/p/596339740 | https://arxiv.org/pdf/2211.04557.pdf | https://uditsinghparihar.github.io/APP_OCC/ |
| 2022-12-24 | SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud | SSDA3D:用于点云三维目标检测的半监督域自适应算法 | https://zhuanlan.zhihu.com/p/594080232 | https://arxiv.org/pdf/2212.02845.pdf | https://github.com/yinjunbo/SSDA3D |
| 2022-12-22 | CONTEXT-AWARE DATA AUGMENTATION FOR LIDAR 3D OBJECT DETECTION | 激光雷达三维目标检测中的上下文感知数据增强 | https://zhuanlan.zhihu.com/p/593623415 | https://zhuanlan.zhihu.com/p/593623415 | |
| 2022-12-20 | SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields | SceneRF：基于辐射场的自监督单目三维场景重建 | https://zhuanlan.zhihu.com/p/593193238 | https://arxiv.org/pdf/2212.02501.pdf | https://astra-vision.github.io/SceneRF/ |
| 2022-12-20 | Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation | Lite-Mono：一种用于自监督单目深度估计的轻量级CNN和Transformer体系结构 | https://zhuanlan.zhihu.com/p/593062025 | https://arxiv.org/pdf/2211.13202.pdf | https://github.com/noahzn/Lite-Mono |
| 2022-12-18 | 3D Object Aided Self-Supervised Monocular Depth Estimation | 三维目标辅助自监督单目深度估计 | https://zhuanlan.zhihu.com/p/592641555 | https://arxiv.org/pdf/2212.01768.pdf | |
| 2022-12-14 | Gaussian Radar Transformer for Semantic Segmentation in Noisy Radar Data | 高斯Radar Transformer在Radar数据语义分割中的应用 | https://zhuanlan.zhihu.com/p/591880664 | https://arxiv.org/pdf/2212.03690.pdf | |
| 2022-12-13 | Robust Point Cloud Segmentation with Noisy Annotations | 带噪声标注的鲁棒点云分割 | https://zhuanlan.zhihu.com/p/591596771 | https://arxiv.org/pdf/2212.03242.pdf | https://github.com/pleaseconnectwifi/PNAL |
| 2022-12-27 | Wild-Places: A Large-Scale Dataset for Lidar Place Recognition in Unstructured Natural Environments | Wild-Places：非结构化自然环境中大规模数据集的激光雷达位置识别 | https://zhuanlan.zhihu.com/p/594752961 | https://arxiv.org/pdf/2211.12732.pdf | https://csiro-robotics.github.io/Wild-Places/ |
| 2022-12-08 | Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Object Detection | 面向高效紧凑的multi-view三维目标检测的结构化知识蒸馏 | https://zhuanlan.zhihu.com/p/590374321 | https://arxiv.org/pdf/2211.08398.pdf | |
| 2022-12-07 | Progressive Learning with Cross-Window Consistency for Semi-Supervised Semantic Segmentation | 基于跨窗口一致性的半监督语义分割的渐进学习算法 | https://zhuanlan.zhihu.com/p/590084676 | https://arxiv.org/pdf/2211.12425.pdf | |
| 2022-12-07 | Structural Knowledge Distillation for Object Detection | 目标检测的结构化知识蒸馏 | https://zhuanlan.zhihu.com/p/590083270 | https://arxiv.org/pdf/2211.13133.pdf | |
| 2022-12-02 | SAILOR: Scaling Anchors via Insights into Latent Object Representation | SAILOR：通过对潜在目标表示的洞察来缩放anchor | https://zhuanlan.zhihu.com/p/588504784 | https://arxiv.org/pdf/2210.07811.pdf | |
| 2022-12-02 | XC: Exploring Quantitative Use Cases for Explanations in 3D Object Detection | XC：探索三维目标检测中解释的定量用例 | https://zhuanlan.zhihu.com/p/588504549 | https://arxiv.org/pdf/2210.11590.pdf | |
| 2022-11-30 | PAI3D: Painting Adaptive Instance-Prior for 3D Object Detection | PAI3D：用于3D目标检测的自适应实例先验绘Painting | https://zhuanlan.zhihu.com/p/587986901 | https://arxiv.org/pdf/2211.08055.pdf | |
| 2022-11-30 | Hyperbolic Cosine Transformer for LiDAR 3D Object Detection* | 用于激光雷达3D目标检测的双曲余弦Transformer | https://zhuanlan.zhihu.com/p/587987589 | https://arxiv.org/ftp/arxiv/papers/2211/2211.05580.pdf | |
| 2022-11-28 | You Only Label Once: 3D Box Adaptation from Point Cloud to Image via Semi-Supervised Learning | 只标注一次! You Only Label Once：基于半监督学习的点云到图像的3D box自适应 | https://zhuanlan.zhihu.com/p/587542491 | https://arxiv.org/pdf/2211.09302.pdf | |
| 2022-11-26 | PointSee: Image Enhances Point Cloud | PointSee：使用图像增强点云 | https://zhuanlan.zhihu.com/p/586824434 | https://arxiv.org/pdf/2211.01664.pdf | |
| 2022-11-26 | Multi-Camera Multi-Object Tracking on the Move via Single-Stage Global Association Approach | 基于单阶段全局关联的多摄像机多目标运动跟踪 | https://zhuanlan.zhihu.com/p/586818421 | https://arxiv.org/pdf/2211.09663.pdf | |
| 2022-11-25 | Recursive Cross-View: Use Only 2D Detectors to Achieve 3D Object Detection without 3D Annotations | Recursive Cross-View:仅使用2D检测器实现无需3D标注的3D目标检测 | https://zhuanlan.zhihu.com/p/586586304 | https://arxiv.org/ftp/arxiv/papers/2211/2211.07108.pdf | |
| 2022-11-25 | ImLiDAR: Cross-Sensor Dynamic Message Propagation Network for 3D Object Detection | IMLIDAR：用于三维目标检测的跨传感器动态消息传播网络 | https://zhuanlan.zhihu.com/p/586585740 | https://arxiv.org/pdf/2211.09518.pdf | |
| 2022-11-23 | DeepMLE: A Robust Deep Maximum Likelihood Estimator for Two-view Structure from Motion | DeepMLE：一种基于SFM的双视结构鲁棒深度极大似然估计器 | https://zhuanlan.zhihu.com/p/586134028 | https://arxiv.org/pdf/2210.05517.pdf | |
| 2022-11-23 | CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds | CAGroup3D:基于类感知的点云三维目标检测分组算法 | https://zhuanlan.zhihu.com/p/586131844 | https://arxiv.org/pdf/2210.04264.pdf | https://github.com/Haiyang-W/CAGroup3D |
| 2022-11-21 | Boosting Monocular 3D Object Detection with Object-Centric Auxiliary Depth Supervision | 以物体为中心的辅助深度监督增强单目3D目标检测 | https://zhuanlan.zhihu.com/p/585504648 | https://arxiv.org/pdf/2210.16574.pdf | |
| 2022-11-21 | Multi-Camera Calibration Free BEV Representation for 3D Object Detection | 用于三维目标检测的多摄像机无标定BEV表示 | https://zhuanlan.zhihu.com/p/585506429 | https://arxiv.org/pdf/2210.17252.pdf | |
| 2022-11-14 | Li3DeTr: A LiDAR based 3D Detection Transformer | Li3DeTr:一种基于激光雷达的三维检测Transformer | https://zhuanlan.zhihu.com/p/583415796 | https://arxiv.org/pdf/2210.15365.pdf | |
| 2022-11-14 | NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields | NeRF-SLAM: 具有神经辐射场的实时密集单目SLAM | https://zhuanlan.zhihu.com/p/583419503 | https://arxiv.org/pdf/2210.13641.pdf | |
| 2022-11-13 | TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM | TripletTrack：基于三元组嵌入和LSTM的三维目标跟踪 | https://zhuanlan.zhihu.com/p/583070856 | https://arxiv.org/pdf/2210.16204.pdf | |
| 2022-11-13 | MSF3DDETR: Multi-Sensor Fusion 3D Detection Transformer for Autonomous Driving | MSF3DDETR: 用于自动驾驶的多传感器融合3D检测Transformer | https://zhuanlan.zhihu.com/p/583068183 | https://arxiv.org/pdf/2210.15316.pdf | |
| 2022-11-09 | VP-SLAM: A Monocular Real-time Visual SLAM with Points, Lines and Vanishing Points | VP-SLAM：一种具有点、线和消失点的单目实时视觉SLAM | https://zhuanlan.zhihu.com/p/581976777 | https://arxiv.org/pdf/2210.12756.pdf | |
| 2022-11-09 | Strong-TransCenter: Improved Multi-Object Tracking based on Transformers with Dense Representations | Strong-TransCenter：改进的基于稠密表示的Transformer的多目标跟踪 | https://zhuanlan.zhihu.com/p/581975219 | https://arxiv.org/pdf/2210.13570.pdf | https://github.com/amitgalor18/STC_Tracker |
| 2022-11-09 | High-Resolution Depth Estimation for 360◦ Panoramas through Perspective and Panoramic Depth Images Registration | 通过透视与全景深度图像配准实现360°全景图的高分辨率深度估计 | https://zhuanlan.zhihu.com/p/581970766 | https://arxiv.org/pdf/2210.10414.pdf | |
| 2022-11-03 | CenterLineDet: CenterLine Graph Detection for Road Lanes with Vehicle-mounted Sensors by Transformer for HD Map Generation | CenterLineDet：基于transformer的车载传感器的车道中心线图检测（用于高清地图创建） | https://zhuanlan.zhihu.com/p/580182205 | https://arxiv.org/pdf/2209.07734.pdf | https://tonyxuqaq.github.io/projects/CenterLineDet/ |
| 2022-11-03 | CurveFormer: 3D Lane Detection by Curve Propagation with Curve Queries and Attention | CurveFormer:基于曲线传播和曲线查询的三维车道检测 | https://zhuanlan.zhihu.com/p/580184768 | https://arxiv.org/pdf/2209.07989.pdf | |
| 2022-11-03 | Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather | 大雾天气下自动驾驶的域自适应目标检测 | https://zhuanlan.zhihu.com/p/580188194 | https://arxiv.org/pdf/2210.15176.pdf | https://github.com/jinlong17/DA-Detect |
| 2022-11-03 | Row-wise LiDAR Lane Detection Network with Lane Correlation Refinement | 基于车道相关细化的行内(Row-wise)激光雷达车道检测网络 | https://zhuanlan.zhihu.com/p/580187274 | https://arxiv.org/pdf/2210.08745.pdf | |
| 2022-10-31 | Rethinking the compositionality of point clouds through regularization in the hyperbolic space | NeurIPS 2022 通过双曲空间中的正则化重新思考点云的组成性 | https://zhuanlan.zhihu.com/p/579179736 | https://arxiv.org/pdf/2209.10318v1.pdf | https://github.com/diegovalsesia/HyCoRe |
| 2022-10-31 | Integrated Decision and Control for High-Level Automated Vehicles by Mixed Policy Gradient and Its Experiment Verification | 混合策略梯度对高级自动化车辆的集成决策与控制及其实验验证 | https://zhuanlan.zhihu.com/p/579176804 | https://arxiv.org/pdf/2210.10613v1.pdf | |
| 2022-10-31 | Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real Data | CoRL 2022 Sim-to-Real via Sim-to-Seg：没有真实数据的端到端越野自动驾驶 | https://zhuanlan.zhihu.com/p/579178473 | https://arxiv.org/pdf/2210.14721v1.pdf | |
| 2022-10-31 | Let Images Give You More: Point Cloud Cross-Modal Training for Shape Analysis | NIPS 2022 让图像给你更多: 形状分析的点云交叉模态训练 | https://zhuanlan.zhihu.com/p/579180596 | https://arxiv.org/pdf/2210.04208v1.pdf | https://github.com/ZhanHeshen/PointCMT |
| 2022-10-28 | SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds | SWFormer：点云3D目标检测的稀疏窗口Transformer | https://zhuanlan.zhihu.com/p/577985802 | https://arxiv.org/pdf/2210.07372v1.pdf | |
| 2022-10-27 | BoundED: Neural Boundary and Edge Detection in 3D Point Clouds via Local Neighborhood Statistics | BoundED: 基于局部邻域统计的3D点云神经边界和边缘检测 | https://zhuanlan.zhihu.com/p/577683400 | https://arxiv.org/pdf/2210.13305v1.pdf | |
| 2022-10-27 | Dual-Curriculum Teacher for Domain-Inconsistent Object Detection in Autonomous Driving | DucTeacher：自动驾驶域不一致下的目标检测 | https://zhuanlan.zhihu.com/p/577683900 | https://arxiv.org/pdf/2210.08748v1.pdf | |
| 2022-10-25 | An Efficient FPGA Accelerator for Point Cloud | 一种高效的点云FPGA加速器 | https://zhuanlan.zhihu.com/p/577253942 | https://arxiv.org/pdf/2210.07803.pdf | |
| 2022-10-24 | Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection | 3D目标检测中的同质多模态特征融合与交互（ECCV2022） | https://zhuanlan.zhihu.com/p/576470649 | https://arxiv.org/pdf/2210.09615.pdf | |
| 2022-10-21 | CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection | Cramnet：基于射线约束交叉注意的鲁棒三维目标检测的Camera-Radar融合 | https://zhuanlan.zhihu.com/p/576042183 | https://arxiv.org/pdf/2210.09267.pdf | |
| 2022-10-21 | Instance Segmentation with Cross-Modal Consistency | 具有跨模态一致性的实例分割 | https://zhuanlan.zhihu.com/p/576037478 | https://arxiv.org/pdf/2210.08113.pdf | |
| 2022-10-14 | Towards Efficient 3D Object Detection with Knowledge Distillation | 通过知识蒸馏实现高效的3D目标检测 | https://zhuanlan.zhihu.com/p/573732965 | https://arxiv.org/pdf/2205.15156.pdf | https://github.com/CVMI-Lab/SparseKD |
| 2022-10-14 | CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection | CrossDTR：基于多目深度引导的3D目标检测 | https://zhuanlan.zhihu.com/p/572556344 | https://arxiv.org/pdf/2209.13507.pdf | https://github.com/sty61010/CrossDTR |
| 2022-10-12 | Unsupervised confidence for LiDAR depth maps and applications | IROS 2022 | 激光雷达深度图的无监督置信度及其应用 | https://zhuanlan.zhihu.com/p/573009801 | https://arxiv.org/pdf/2210.03118v1.pdf | https://github.com/andreaconti/lidar-confidence |
| 2022-10-11 | TIME WILL TELL: NEW OUTLOOKS AND A BASELINE FOR TEMPORAL MULTI-VIEW 3D OBJECT DETECTION | SOLOFusion：时空多视图3D目标检测的新基线 | https://zhuanlan.zhihu.com/p/572649410 | https://arxiv.org/pdf/2210.02443v1.pdf | https://github.com/Divadi/SOLOFusion |
| 2022-10-10 | LOPR: Latent Occupancy PRediction using Generative Models | LOPR: 使用生成模型进行潜在occupancy预测 | https://zhuanlan.zhihu.com/p/572294360 | https://arxiv.org/pdf/2210.01249v1.pdf | https://github.com/sisl/LOPR |
| 2022-10-09 | D-Align: Dual Query Co-attention Network for 3D Object Detection Based on Multi-frame Point Cloud Sequence | D-Align: 基于多帧点云序列的三维目标检测双查询协同attention网络 | https://zhuanlan.zhihu.com/p/571955426 | https://arxiv.org/pdf/2210.00087v1.pdf | |
| 2022-10-06 | DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment | DirectTracker: 使用直接图像对齐和光度束调整的3D多目标跟踪 | https://zhuanlan.zhihu.com/p/570955927 | https://arxiv.org/pdf/2209.14965v1.pdf | https://cvg.cit.tum.de/research/vslam/directtracker |
| 2022-09-29 | ERASE-Net: Efficient Segmentation Networks for Automotive Radar Signals | ERASE-Net: 自动驾驶Radar数据的高效分割网络 | https://zhuanlan.zhihu.com/p/569510004 | https://arxiv.org/pdf/2209.12940v1.pdf | |
| 2022-09-28 | Exploring Attention GAN for Vehicle Motion Prediction | 探索用于车辆运动预测的attention GAN | https://zhuanlan.zhihu.com/p/569147057 | https://arxiv.org/pdf/2209.12674v1.pdf | https://github.com/Cram3r95/mapfe4mp |
| 2022-09-28 | Attitude-Guided Loop Closure for Cameras with Negative Plane | 负平面相机的姿态引导闭环 | https://zhuanlan.zhihu.com/p/569151652 | https://arxiv.org/ | https://github.com/flysoaryun/LF-VISLAM |
| 2022-09-26 | R3LIVE++: A Robust, Real-time, Radiance reconstruction package with a tightly-coupled LiDAR-Inertial-Visual state Estimator | R3LIVE++：一个鲁棒实时的重建package！具有紧密耦合的激光雷达惯性视觉状态估计器 | https://zhuanlan.zhihu.com/p/568436911 | https://arxiv.org/pdf/2209.03666v1.pdf | https://github.com/hku-mars/r3live |
| 2022-09-23 | GANet: Goal Area Network for Motion Forecasting | GANet：运动预测的目标区域网络 | https://zhuanlan.zhihu.com/p/567605999 | https://arxiv.org/pdf/2209.09723v1.pdf | |
| 2022-09-22 | A Dual-Cycled Cross-View Transformer Network for Unified Road Layout Estimation and 3D Object Detection in the Bird’s-Eye-View | BEV中统一道路布局估计和3D目标检测的Transformer网络 | https://zhuanlan.zhihu.com/p/567239638 | https://arxiv.org/pdf/2209.08844v1.pdf | |
| 2022-09-22 | Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving | 统一自动驾驶多任务协同训练的有效适应 | https://zhuanlan.zhihu.com/p/567235140 | https://arxiv.org/pdf/2209.08953v1.pdf | |
| 2022-09-20 | GATraj: A Graph- and Attention-based Multi-Agent Trajectory Prediction Model | GATraj：基于图和注意力的多智能体轨迹预测模型 | https://zhuanlan.zhihu.com/p/566497492 | https://arxiv.org/pdf/2209.07857v1.pdf | https://github.com/mengmengliu1998/gatraj |
| 2022-09-19 | CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer | CRAFT：毫米波雷达与相机融合3D目标检测 | https://zhuanlan.zhihu.com/p/566114804 | https://arxiv.org/pdf/2209.06535v1.pdf | |
| 2022-09-15 | SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation | 3DV2022 高效鲁棒！SVNet：SO(3) 等变在点云表示上遇到二值化 | https://zhuanlan.zhihu.com/p/564844717 | https://arxiv.org/pdf/2209.05924v1.pdf | https://github.com/hellozhuo/svnet |
| 2022-09-15 | CenterFormer: Center-based Transformer for 3D Object Detection | ECCV2022 oral CenterFormer：用于 3D 目标检测的Transformer | https://zhuanlan.zhihu.com/p/564838907 | https://arxiv.org/pdf/2209.05588v1.pdf | https://github.com/TuSimple/centerformer |
| 2022-09-14 | Multi-modal Streaming 3D Object Detection | 多模态流式3D目标检测 | https://zhuanlan.zhihu.com/p/564467078 | https://arxiv.org/pdf/2209.04966v1.pdf | |
| 2022-09-13 | Real-time 3D Single Object Tracking with Transformer | 使用 Transformer 进行实时3D单目标跟踪 | https://zhuanlan.zhihu.com/p/563331685 | https://arxiv.org/pdf/2209.00860v1.pdf | https://github.com/shanjiayao/PTT |
| 2022-09-13 | MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection | MSMDFusion：将多尺度激光雷达和相机与多深度种子融合以进行3D目标检测 | https://zhuanlan.zhihu.com/p/563331218 | https://arxiv.org/pdf/2209.03102v1.pdf | https://github.com/SxJyJay/MSMDFusion |
| 2022-09-12 | LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds | ECCV2022 LESS：LiDAR 点云的标签高效语义分割 | https://zhuanlan.zhihu.com/p/563532266 | https://cseweb.ucsd.edu/~mil070/projects/ECCV2022/paper.pdf | |
| 2022-09-09 | CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusion | CAMO-MOT：基于LiDAR-Camera 融合的3D 多目标跟踪优化方法 | https://zhuanlan.zhihu.com/p/562755238 | https://arxiv.org/pdf/2209.02540v2.pdf | |
| 2022-09-08 | DeepInteraction: 3D Object Detection via Modality Interaction | DeepInteraction：通过模态交互进行 3D 对象检测 | https://zhuanlan.zhihu.com/p/562386666 | https://arxiv.org/pdf/2208.11112v2.pdf | https://github.com/fudan-zvg/DeepInteraction |
This repository was mainly written by Rujia Wang.
If you have any questions about the paper list, please do not hesitate to email me or open an issue on GitHub.