{"total":157,"rows":[{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850,"area":null},{"id":"2104.10133","title":"Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset","created":"2021-04-20","cited_by_count":537,"area":null},{"id":"2107.06307","title":"HDMapNet: An Online HD Map Construction and Evaluation Framework","created":"2021-07-13","cited_by_count":281,"area":null},{"id":"2109.02497","title":"Voxel Transformer for 3D Object Detection","created":"2021-09-06","cited_by_count":247,"area":null},{"id":"2206.08920","title":"VectorMapNet: End-to-end Vectorized HD Map Learning","created":"2022-06-17","cited_by_count":245,"area":null},{"id":"2102.00463","title":"PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection","created":"2021-01-31","cited_by_count":232,"area":null},{"id":"2203.08195","title":"DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection","created":"2022-03-15","cited_by_count":224,"area":null},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212,"area":null},{"id":"2203.10642","title":"FUTR3D: A Unified Sensor Fusion Framework for 3D Detection","created":"2022-03-20","cited_by_count":194,"area":null},{"id":"2112.06375","title":"Embracing Single Stride 3D Object Detector with Sparse Transformer","created":"2021-12-13","cited_by_count":193,"area":null},{"id":"2103.12978","title":"RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation","created":"2021-03-24","cited_by_count":173,"area":null},{"id":"2103.05073","title":"Offboard 3D Object Detection from Point Cloud Sequences","created":"2021-03-08","cited_by_count":145,"area":null},{"id":"2103.10039","title":"RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection","created":"2021-03-18","cited_by_count":140,"area":null},{"id":"2203.11139","title":"Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds","created":"2022-03-21","cited_by_count":131,"area":null},{"id":"2103.15297","title":"LiDAR R-CNN: An Efficient and Universal 3D Object Detector","created":"2021-03-29","cited_by_count":129,"area":null},{"id":"2106.13365","title":"RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection","created":"2021-06-25","cited_by_count":115,"area":null},{"id":"2108.10723","title":"Improving 3D Object Detection with Channel-wise Transformer","created":"2021-08-23","cited_by_count":108,"area":null},{"id":"2103.14962","title":"Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation","created":"2021-03-27","cited_by_count":107,"area":null},{"id":"2106.10823","title":"3D Object Detection for Autonomous Driving: A Survey","created":"2021-06-21","cited_by_count":106,"area":null},{"id":"2203.10314","title":"Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds","created":"2022-03-19","cited_by_count":102,"area":null},{"id":"2108.06709","title":"SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation","created":"2021-08-15","cited_by_count":94,"area":null},{"id":"2210.07372","title":"SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds","created":"2022-10-13","cited_by_count":92,"area":null},{"id":"2112.09205","title":"AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds","created":"2021-12-16","cited_by_count":88,"area":null},{"id":"2207.10035","title":"Fully Sparse 3D Object Detection","created":"2022-07-20","cited_by_count":84,"area":null},{"id":"2109.02499","title":"Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection","created":"2021-09-06","cited_by_count":79,"area":null},{"id":"2308.07732","title":"UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation","created":"2023-08-15","cited_by_count":74,"area":null},{"id":"2103.16054","title":"3D-MAN: 3D Multi-frame Attention Network for Object Detection","created":"2021-03-30","cited_by_count":73,"area":null},{"id":"2301.08739","title":"FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer","created":"2023-01-20","cited_by_count":73,"area":null},{"id":"2203.05662","title":"Point Density-Aware Voxels for LiDAR 3D Object Detection","created":"2022-03-10","cited_by_count":70,"area":null},{"id":"2205.07002","title":"Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmap","created":"2022-05-14","cited_by_count":59,"area":null},{"id":"2210.08061","title":"Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving","created":"2022-10-14","cited_by_count":59,"area":null},{"id":"2110.06923","title":"Object DGCNN: 3D Object Detection using Dynamic Graphs","created":"2021-10-13","cited_by_count":58,"area":null},{"id":"2112.02205","title":"Behind the Curtain: Learning Occluded Shapes for 3D Object Detection","created":"2021-12-04","cited_by_count":58,"area":null},{"id":"2308.04556","title":"FocalFormer3D : Focusing on Hard Instance for 3D Object Detection","created":"2023-08-08","cited_by_count":58,"area":null},{"id":"2109.05441","title":"Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception","created":"2021-09-12","cited_by_count":57,"area":null},{"id":"2212.03010","title":"GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds","created":"2022-12-06","cited_by_count":57,"area":null},{"id":"2108.10312","title":"Exploring Simple 3D Multi-Object Tracking for Autonomous Driving","created":"2021-08-23","cited_by_count":56,"area":null},{"id":"2305.04925","title":"PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds","created":"2023-05-08","cited_by_count":54,"area":null},{"id":"2103.01306","title":"Scalable Scene Flow from Point Clouds in the Real World","created":"2021-03-01","cited_by_count":50,"area":null},{"id":"2203.09704","title":"VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention","created":"2022-03-18","cited_by_count":48,"area":null},{"id":"2207.10316","title":"AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection","created":"2022-07-21","cited_by_count":46,"area":null},{"id":"2310.20234","title":"HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds","created":"2023-10-31","cited_by_count":45,"area":null},{"id":"2109.01066","title":"4D-Net for Learned Multi-Modal Alignment","created":"2021-09-02","cited_by_count":44,"area":null},{"id":"2203.15882","title":"Learning to Detect Mobile Objects from LiDAR Scans Without Labels","created":"2022-03-29","cited_by_count":44,"area":null},{"id":"2208.03624","title":"Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph","created":"2022-08-07","cited_by_count":42,"area":null},{"id":"2106.13381","title":"To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels","created":"2021-06-25","cited_by_count":39,"area":null},{"id":"2207.00531","title":"Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Clouds","created":"2022-07-01","cited_by_count":39,"area":null},{"id":"2211.15656","title":"SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generation","created":"2022-11-28","cited_by_count":39,"area":null},{"id":"2305.08808","title":"GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training","created":"2023-05-15","cited_by_count":38,"area":null},{"id":"2204.01026","title":"STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes","created":"2022-04-03","cited_by_count":35,"area":null},{"id":"2103.09422","title":"YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection","created":"2021-03-17","cited_by_count":34,"area":null},{"id":"2108.07511","title":"LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation","created":"2021-08-17","cited_by_count":34,"area":null},{"id":"2103.02093","title":"Pseudo-labeling for Scalable 3D Object Detection","created":"2021-03-02","cited_by_count":32,"area":null},{"id":"2107.04327","title":"Score refinement for confidence-based 3D multi-object tracking","created":"2021-07-09","cited_by_count":32,"area":null},{"id":"2210.07442","title":"Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds","created":"2022-10-14","cited_by_count":32,"area":null},{"id":"2301.02562","title":"Super Sparse 3D Object Detection","created":"2023-01-05","cited_by_count":32,"area":null},{"id":"2306.06023","title":"DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds","created":"2023-06-09","cited_by_count":31,"area":null},{"id":"2210.09267","title":"CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection","created":"2022-10-17","cited_by_count":30,"area":null},{"id":"2401.16122","title":"DeFlow: Decoder of Scene Flow Network in Autonomous Driving","created":"2024-01-29","cited_by_count":30,"area":null},{"id":"2310.05699","title":"Uni3DETR: Unified 3D Detection Transformer","created":"2023-10-09","cited_by_count":27,"area":null},{"id":"2107.14391","title":"From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection","created":"2021-07-30","cited_by_count":24,"area":null},{"id":"2207.02466","title":"GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation","created":"2022-07-06","cited_by_count":24,"area":null},{"id":"2308.12113","title":"Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey","created":"2023-08-23","cited_by_count":24,"area":null},{"id":"2108.03648","title":"From Voxel to Point: IoU-guided 3D Object Detection for Point Cloud with Voxel-to-Point Decoder","created":"2021-08-08","cited_by_count":23,"area":null},{"id":"2111.15363","title":"Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding","created":"2021-11-30","cited_by_count":22,"area":null},{"id":"2312.08876","title":"OpenSight: A Simple Open-Vocabulary Framework for LiDAR-Based Object Detection","created":"2023-12-12","cited_by_count":22,"area":null},{"id":"2207.09332","title":"Rethinking IoU-based Optimization for Single-stage 3D Object Detection","created":"2022-07-19","cited_by_count":19,"area":null},{"id":"2210.08375","title":"Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining","created":"2022-10-15","cited_by_count":19,"area":null},{"id":"2104.10772","title":"MVFuseNet: Improving End-to-End Object Detection and Motion Forecasting through Multi-View Fusion of LiDAR Data","created":"2021-04-21","cited_by_count":18,"area":null},{"id":"2106.07545","title":"PolarStream: Streaming Lidar Object Detection and Segmentation with Polar Pillars","created":"2021-06-14","cited_by_count":18,"area":null},{"id":"2112.07787","title":"Revisiting 3D Object Detection From an Egocentric Perspective","created":"2021-12-14","cited_by_count":18,"area":null},{"id":"2203.13394","title":"Point2Seq: Detecting 3D Objects as Sequences","created":"2022-03-25","cited_by_count":15,"area":null},{"id":"2406.04426","title":"DeTra: A Unified Model for Object Detection and Trajectory Forecasting","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2209.10733","title":"FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection","created":"2022-09-22","cited_by_count":14,"area":null},{"id":"2209.15215","title":"INT: Towards Infinite-frames 3D Detection with An Efficient Framework","created":"2022-09-30","cited_by_count":14,"area":null},{"id":"2308.05988","title":"MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detection","created":"2023-08-11","cited_by_count":14,"area":null},{"id":"2308.13323","title":"SVQNet: Sparse Voxel-Adjacent Query Network for 4D Spatio-Temporal LiDAR Semantic Segmentation","created":"2023-08-25","cited_by_count":14,"area":null},{"id":"2405.18734","title":"Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encoder","created":"2024-05-29","cited_by_count":14,"area":null},{"id":"2108.03634","title":"Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloud","created":"2021-08-08","cited_by_count":13,"area":null},{"id":"2208.11658","title":"AGO-Net: Association-Guided 3D Point Cloud Object Detection Network","created":"2022-08-24","cited_by_count":12,"area":null},{"id":"2308.10421","title":"UniM$^2$AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving","created":"2023-08-21","cited_by_count":12,"area":null},{"id":"2110.09355","title":"FAST3D: Flow-Aware Self-Training for 3D Object Detectors","created":"2021-10-18","cited_by_count":10,"area":null},{"id":"2306.17440","title":"STTracker: Spatio-Temporal Tracker for 3D Single Object Tracking","created":"2023-06-30","cited_by_count":10,"area":null},{"id":"2204.01719","title":"RestoreX-AI: A Contrastive Approach towards Guiding Image Restoration via Explainable AI Systems","created":"2022-04-03","cited_by_count":9,"area":null},{"id":"2308.03982","title":"PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection","created":"2023-08-08","cited_by_count":9,"area":null},{"id":"2408.06832","title":"FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving","created":"2024-08-13","cited_by_count":9,"area":null},{"id":"2202.06263","title":"LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling","created":"2022-02-13","cited_by_count":8,"area":null},{"id":"2208.08621","title":"Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes","created":"2022-08-18","cited_by_count":8,"area":null},{"id":"2210.13488","title":"LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations","created":"2022-10-24","cited_by_count":8,"area":null},{"id":"2403.10036","title":"SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception","created":"2024-03-15","cited_by_count":8,"area":null},{"id":"2404.19531","title":"MoST: Multi-modality Scene Tokenization for Motion Prediction","created":"2024-04-30","cited_by_count":8,"area":null},{"id":"2103.13001","title":"X-view: Non-egocentric Multi-View 3D Object Detector","created":"2021-03-24","cited_by_count":7,"area":null},{"id":"2206.13082","title":"PST: Plant segmentation transformer for 3D point clouds of rapeseed plants at the podding stage","created":"2022-06-27","cited_by_count":7,"area":null},{"id":"2210.13428","title":"PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds","created":"2022-10-24","cited_by_count":7,"area":null},{"id":"2211.08248","title":"3D Cascade RCNN: High Quality Object Detection in Point Clouds","created":"2022-11-15","cited_by_count":7,"area":null},{"id":"2503.08421","title":"Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels","created":"2025-03-11","cited_by_count":7,"area":null},{"id":"2101.02385","title":"Safety-Oriented Pedestrian Motion and Scene Occupancy Forecasting","created":"2021-01-07","cited_by_count":6,"area":null},{"id":"2106.11239","title":"2D vs. 3D LiDAR-based Person Detection on Mobile Robots","created":"2021-06-21","cited_by_count":6,"area":null},{"id":"2204.09337","title":"Sequential Point Clouds: A Survey","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2305.15836","title":"Improved Multi-Scale Grid Rendering of Point Clouds for Radar Object Detection Networks","created":"2023-05-25","cited_by_count":6,"area":null}],"next_cursor":"100"}