{"total":142,"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":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336,"area":null},{"id":"2303.11301","title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","created":"2023-03-20","cited_by_count":222,"area":null},{"id":"2206.00630","title":"Unifying Voxel-based Representation with Transformer for 3D Object Detection","created":"2022-06-01","cited_by_count":202,"area":null},{"id":"2206.09474","title":"3D Object Detection for Autonomous Driving: A Comprehensive Survey","created":"2022-06-19","cited_by_count":132,"area":null},{"id":"2208.11112","title":"DeepInteraction: 3D Object Detection via Modality Interaction","created":"2022-08-23","cited_by_count":125,"area":null},{"id":"2303.12766","title":"Spherical Transformer for LiDAR-based 3D Recognition","created":"2023-03-22","cited_by_count":125,"area":null},{"id":"2303.11040","title":"Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving","created":"2023-03-20","cited_by_count":114,"area":null},{"id":"2304.00962","title":"RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding","created":"2023-04-03","cited_by_count":94,"area":null},{"id":"2303.02314","title":"Virtual Sparse Convolution for Multimodal 3D Object Detection","created":"2023-03-04","cited_by_count":81,"area":null},{"id":"2303.03595","title":"LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion","created":"2023-03-07","cited_by_count":80,"area":null},{"id":"2209.09385","title":"LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception","created":"2022-09-19","cited_by_count":74,"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":"2206.10555","title":"LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs","created":"2022-06-21","cited_by_count":72,"area":null},{"id":"2301.01283","title":"Cross Modal Transformer: Towards Fast and Robust 3D Object Detection","created":"2023-01-03","cited_by_count":70,"area":null},{"id":"2406.10700","title":"Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection","created":"2024-06-15","cited_by_count":66,"area":"ssm"},{"id":"2308.04556","title":"FocalFormer3D : Focusing on Hard Instance for 3D Object Detection","created":"2023-08-08","cited_by_count":58,"area":null},{"id":"2403.15241","title":"IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection","created":"2024-03-22","cited_by_count":57,"area":null},{"id":"2403.05817","title":"SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection","created":"2024-03-09","cited_by_count":52,"area":null},{"id":"2209.02540","title":"CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusion","created":"2022-09-06","cited_by_count":50,"area":null},{"id":"2404.06892","title":"SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Driving","created":"2024-04-10","cited_by_count":47,"area":"driving"},{"id":"2309.01692","title":"Mask-Attention-Free Transformer for 3D Instance Segmentation","created":"2023-09-04","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":"2302.02367","title":"FastPillars: A Deployment-friendly Pillar-based 3D Detector","created":"2023-02-05","cited_by_count":39,"area":null},{"id":"2210.06778","title":"X-Align: Cross-Modal Cross-View Alignment for Bird's-Eye-View Segmentation","created":"2022-10-13","cited_by_count":38,"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":"2212.02845","title":"SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud","created":"2022-12-06","cited_by_count":37,"area":null},{"id":"2309.14491","title":"Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving","created":"2023-09-25","cited_by_count":37,"area":"driving"},{"id":"2308.03755","title":"FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels","created":"2023-08-07","cited_by_count":34,"area":null},{"id":"2310.08261","title":"GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection","created":"2023-10-12","cited_by_count":34,"area":null},{"id":"2303.12621","title":"OcTr: Octree-based Transformer for 3D Object Detection","created":"2023-03-22","cited_by_count":32,"area":null},{"id":"2304.12310","title":"Fully Sparse Fusion for 3D Object Detection","created":"2023-04-24","cited_by_count":29,"area":null},{"id":"2311.07152","title":"Detecting As Labeling: Rethinking LiDAR-camera Fusion in 3D Object Detection","created":"2023-11-13","cited_by_count":28,"area":null},{"id":"2406.12214","title":"Is Your HD Map Constructor Reliable under Sensor Corruptions?","created":"2024-06-18","cited_by_count":28,"area":null},{"id":"2310.05699","title":"Uni3DETR: Unified 3D Detection Transformer","created":"2023-10-09","cited_by_count":27,"area":null},{"id":"2209.14201","title":"Spatial Pruned Sparse Convolution for Efficient 3D Object Detection","created":"2022-09-28","cited_by_count":26,"area":null},{"id":"2303.16094","title":"LinK: Linear Kernel for LiDAR-based 3D Perception","created":"2023-03-28","cited_by_count":26,"area":null},{"id":"2406.10224","title":"EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models","created":"2024-06-14","cited_by_count":26,"area":null},{"id":"2305.04075","title":"PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videos","created":"2023-05-06","cited_by_count":22,"area":null},{"id":"2308.06635","title":"3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking","created":"2023-08-12","cited_by_count":21,"area":null},{"id":"2401.03907","title":"RoboFusion: Towards Robust Multi-Modal 3D Object Detection via SAM","created":"2024-01-08","cited_by_count":20,"area":null},{"id":"2404.04629","title":"DifFUSER: Diffusion Model for Robust Multi-Sensor Fusion in 3D Object Detection and BEV Segmentation","created":"2024-04-06","cited_by_count":18,"area":"diffusion"},{"id":"2409.16149","title":"MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2308.09247","title":"Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos","created":"2023-08-18","cited_by_count":16,"area":null},{"id":"2403.15173","title":"LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels","created":"2024-03-22","cited_by_count":15,"area":null},{"id":"2211.09375","title":"3D-QueryIS: A Query-based Framework for 3D Instance Segmentation","created":"2022-11-17","cited_by_count":14,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2401.02702","title":"VoxelNextFusion: A Simple, Unified and Effective Voxel Fusion Framework for Multi-Modal 3D Object Detection","created":"2024-01-05","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":"2411.15016","title":"MSSF: A 4D Radar and Camera Fusion Framework With Multi-Stage Sampling for 3D Object Detection in Autonomous Driving","created":"2024-11-22","cited_by_count":14,"area":null},{"id":"2405.16873","title":"ContrastAlign: Toward Robust BEV Feature Alignment via Contrastive Learning for Multi-Modal 3D Object Detection","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"2407.11569","title":"SFPNet: Sparse Focal Point Network for Semantic Segmentation on General LiDAR Point Clouds","created":"2024-07-16","cited_by_count":13,"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":"2508.16408","title":"SAMFusion: Sensor-Adaptive Multimodal Fusion for 3D Object Detection in Adverse Weather","created":"2025-08-22","cited_by_count":12,"area":null},{"id":"2211.13529","title":"3D Dual-Fusion: Dual-Domain Dual-Query Camera-LiDAR Fusion for 3D Object Detection","created":"2022-11-24","cited_by_count":11,"area":null},{"id":"2212.05265","title":"Multi-Sem Fusion: Multimodal Semantic Fusion for 3D Object Detection","created":"2022-12-10","cited_by_count":11,"area":null},{"id":"2303.12194","title":"LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perception","created":"2023-03-21","cited_by_count":11,"area":null},{"id":"2403.13443","title":"Fast-Poly: A Fast Polyhedral Framework For 3D Multi-Object Tracking","created":"2024-03-20","cited_by_count":11,"area":null},{"id":"2403.07372","title":"Eliminating Cross-modal Conflicts in BEV Space for LiDAR-Camera 3D Object Detection","created":"2024-03-12","cited_by_count":10,"area":null},{"id":"2503.12009","title":"UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection","created":"2025-03-15","cited_by_count":10,"area":"ssm"},{"id":"2307.00347","title":"Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection","created":"2023-07-01","cited_by_count":8,"area":null},{"id":"2312.14919","title":"Lift-Attend-Splat: Bird's-eye-view camera-lidar fusion using transformers","created":"2023-12-22","cited_by_count":8,"area":null},{"id":"2404.11764","title":"Multimodal 3D Object Detection on Unseen Domains","created":"2024-04-17","cited_by_count":8,"area":null},{"id":"2407.10200","title":"Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data","created":"2024-07-14","cited_by_count":8,"area":null},{"id":"2411.01584","title":"One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection","created":"2024-11-03","cited_by_count":8,"area":null},{"id":"2502.19630","title":"Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras","created":"2025-02-26","cited_by_count":8,"area":null},{"id":"2206.01381","title":"CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather with a High-quality Real Snow Dataset","created":"2022-06-03","cited_by_count":7,"area":null},{"id":"2305.12853","title":"Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2406.10907","title":"SparseDet: A Simple and Effective Framework for Fully Sparse LiDAR-based 3D Object Detection","created":"2024-06-16","cited_by_count":7,"area":null},{"id":"2209.09464","title":"Rethinking Dimensionality Reduction in Grid-based 3D Object Detection","created":"2022-09-20","cited_by_count":6,"area":null},{"id":"2307.09155","title":"MLF-DET: Multi-Level Fusion for Cross-Modal 3D Object Detection","created":"2023-07-18","cited_by_count":5,"area":null},{"id":"2311.04058","title":"mmFUSION: Multimodal Fusion for 3D Objects Detection","created":"2023-11-07","cited_by_count":5,"area":null},{"id":"2210.07811","title":"SAILOR: Scaling Anchors via Insights into Latent Object Representation","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2305.07713","title":"Multi-Modal 3D Object Detection by Box Matching","created":"2023-05-12","cited_by_count":4,"area":null},{"id":"2402.02738","title":"Improving Robustness of LiDAR-Camera Fusion Model against Weather Corruption from Fusion Strategy Perspective","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2403.09212","title":"PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interest","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2409.11018","title":"Unleashing the Potential of Mamba: Boosting a LiDAR 3D Sparse Detector by Using Cross-Model Knowledge Distillation","created":"2024-09-17","cited_by_count":4,"area":"ssm"},{"id":"2503.17175","title":"Which2comm: An Efficient Collaborative Perception Framework for 3D Object Detection","created":"2025-03-21","cited_by_count":4,"area":null},{"id":"2508.02288","title":"Unleashing the Temporal Potential of Stereo Event Cameras for Continuous-Time 3D Object Detection","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2209.07419","title":"FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detection","created":"2022-09-15","cited_by_count":3,"area":null},{"id":"2301.04058","title":"Rethinking Voxelization and Classification for 3D Object Detection","created":"2023-01-10","cited_by_count":3,"area":null},{"id":"2302.09221","title":"Moby: Empowering 2D Models for Efficient Point Cloud Analytics on the Edge","created":"2023-02-18","cited_by_count":3,"area":null},{"id":"2303.05078","title":"Efficient Transformer-based 3D Object Detection with Dynamic Token Halting","created":"2023-03-09","cited_by_count":3,"area":null},{"id":"2403.14133","title":"3D Object Detection from Point Cloud via Voting Step Diffusion","created":"2024-03-21","cited_by_count":3,"area":null},{"id":"2406.19048","title":"BiCo-Fusion: Bidirectional Complementary LiDAR-Camera Fusion for Semantic- and Spatial-Aware 3D Object Detection","created":"2024-06-27","cited_by_count":3,"area":null},{"id":"2408.13798","title":"Selectively Dilated Convolution for Accuracy-Preserving Sparse Pillar-based Embedded 3D Object Detection","created":"2024-08-25","cited_by_count":3,"area":null},{"id":"2508.00744","title":"Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2304.01519","title":"LiDAR-Based 3D Object Detection via Hybrid 2D Semantic Scene Generation","created":"2023-04-04","cited_by_count":2,"area":null},{"id":"2403.02329","title":"COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2404.18411","title":"SeePerSea: Multi-modal Perception Dataset of In-water Objects for Autonomous Surface Vehicles","created":"2024-04-29","cited_by_count":2,"area":null},{"id":"2405.03884","title":"BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection","created":"2024-05-06","cited_by_count":2,"area":null},{"id":"2407.02098","title":"DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection","created":"2024-07-02","cited_by_count":2,"area":null},{"id":"2501.06550","title":"CoreNet: Conflict Resolution Network for Point-Pixel Misalignment and Sub-Task Suppression of 3D LiDAR-Camera Object Detection","created":"2025-01-11","cited_by_count":2,"area":null},{"id":"2502.02763","title":"Looking Locally: Object-Centric Vision Transformers as Foundation Models for Efficient Segmentation","created":"2025-02-04","cited_by_count":2,"area":null},{"id":"2507.19304","title":"Multistream Network for LiDAR and Camera-based 3D Object Detection in Outdoor Scenes","created":"2025-07-25","cited_by_count":2,"area":null},{"id":"2508.12917","title":"CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection with IoU Joint Prediction","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2510.19215","title":"SFGFusion: Surface Fitting Guided 3D Object Detection with 4D Radar and Camera Fusion","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2602.13772","title":"Offline-Poly: A Polyhedral Framework For Offline 3D Multi-Object Tracking","created":"2026-02-14","cited_by_count":2,"area":null},{"id":"2609.07738","title":"TFTrack: A Template-Free Framework for Efficient 3D Point Cloud Tracking","created":"2026-09-07","cited_by_count":2,"area":null},{"id":"2308.10161","title":"ThermRad: A Multi-modal Dataset for Robust 3D Object Detection under Challenging Conditions","created":"2023-08-20","cited_by_count":1,"area":null}],"next_cursor":"100"}