{"total":107,"rows":[{"id":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327,"area":null},{"id":"2205.02833","title":"Cross-view Transformers for real-time Map-view Semantic Segmentation","created":"2022-05-05","cited_by_count":264,"area":null},{"id":"2108.06417","title":"Is Pseudo-Lidar needed for Monocular 3D Object detection?","created":"2021-08-13","cited_by_count":249,"area":null},{"id":"2104.02323","title":"Objects are Different: Flexible Monocular 3D Object Detection","created":"2021-04-06","cited_by_count":185,"area":null},{"id":"2210.02443","title":"Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection","created":"2022-10-05","cited_by_count":178,"area":null},{"id":"2204.00987","title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","created":"2022-04-03","cited_by_count":168,"area":null},{"id":"2211.10581","title":"Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion","created":"2022-11-19","cited_by_count":162,"area":null},{"id":"2107.13774","title":"Geometry Uncertainty Projection Network for Monocular 3D Object Detection","created":"2021-07-29","cited_by_count":156,"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":"2203.10981","title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","created":"2022-03-21","cited_by_count":109,"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":"2305.14018","title":"Sparse4D v2: Recurrent Temporal Fusion with Sparse Model","created":"2023-05-23","cited_by_count":93,"area":null},{"id":"2108.11127","title":"AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection","created":"2021-08-25","cited_by_count":87,"area":null},{"id":"2103.16470","title":"Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":84,"area":null},{"id":"2403.16440","title":"RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection","created":"2024-03-25","cited_by_count":82,"area":null},{"id":"2203.13608","title":"Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task","created":"2022-03-25","cited_by_count":81,"area":null},{"id":"2201.10830","title":"MonoDistill: Learning Spatial Features for Monocular 3D Object Detection","created":"2022-01-26","cited_by_count":68,"area":null},{"id":"2202.02980","title":"3D Object Detection from Images for Autonomous Driving: A Survey","created":"2022-02-07","cited_by_count":66,"area":null},{"id":"2102.00690","title":"Ground-aware Monocular 3D Object Detection for Autonomous Driving","created":"2021-02-01","cited_by_count":65,"area":null},{"id":"2108.05793","title":"Progressive Coordinate Transforms for Monocular 3D Object Detection","created":"2021-08-12","cited_by_count":52,"area":null},{"id":"2208.12079","title":"Bridging the View Disparity Between Radar and Camera Features for Multi-modal Fusion 3D Object Detection","created":"2022-08-25","cited_by_count":46,"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":"2112.14023","title":"The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection","created":"2021-12-28","cited_by_count":34,"area":null},{"id":"2105.14291","title":"Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview","created":"2021-05-29","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":"2104.09035","title":"Lidar Point Cloud Guided Monocular 3D Object Detection","created":"2021-04-19","cited_by_count":29,"area":null},{"id":"2206.07705","title":"LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection","created":"2022-06-15","cited_by_count":27,"area":null},{"id":"2207.10047","title":"Densely Constrained Depth Estimator for Monocular 3D Object Detection","created":"2022-07-20","cited_by_count":27,"area":null},{"id":"2106.02781","title":"IPS300+: a Challenging Multimodal Dataset for Intersection Perception System","created":"2021-06-05","cited_by_count":26,"area":null},{"id":"2103.08468","title":"Beyond Image to Depth: Improving Depth Prediction using Echoes","created":"2021-03-15","cited_by_count":24,"area":null},{"id":"2204.00754","title":"Homography Loss for Monocular 3D Object Detection","created":"2022-04-02","cited_by_count":24,"area":null},{"id":"2211.01142","title":"OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection","created":"2022-11-02","cited_by_count":24,"area":null},{"id":"2204.11590","title":"Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training","created":"2022-04-25","cited_by_count":22,"area":null},{"id":"2301.04467","title":"FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection","created":"2023-01-10","cited_by_count":21,"area":null},{"id":"2302.10549","title":"MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contexts","created":"2023-02-21","cited_by_count":21,"area":null},{"id":"2104.08797","title":"MonoGRNet: A General Framework for Monocular 3D Object Detection","created":"2021-04-18","cited_by_count":20,"area":null},{"id":"2303.15334","title":"ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box","created":"2023-03-27","cited_by_count":20,"area":null},{"id":"2203.08332","title":"WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection","created":"2022-03-16","cited_by_count":18,"area":null},{"id":"2303.14548","title":"Viewpoint Equivariance for Multi-View 3D Object Detection","created":"2023-03-25","cited_by_count":18,"area":null},{"id":"2111.10332","title":"DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion","created":"2021-11-19","cited_by_count":17,"area":null},{"id":"2110.00464","title":"MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentation","created":"2021-10-01","cited_by_count":16,"area":null},{"id":"2103.03480","title":"IAFA: Instance-aware Feature Aggregation for 3D Object Detection from a Single Image","created":"2021-03-05","cited_by_count":15,"area":null},{"id":"2303.03583","title":"Calibration-free BEV Representation for Infrastructure Perception","created":"2023-03-07","cited_by_count":15,"area":null},{"id":"2109.09628","title":"Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR","created":"2021-09-20","cited_by_count":13,"area":null},{"id":"2112.01914","title":"SGM3D: Stereo Guided Monocular 3D Object Detection","created":"2021-12-03","cited_by_count":13,"area":null},{"id":"2303.10340","title":"3D Data Augmentation for Driving Scenes on Camera","created":"2023-03-18","cited_by_count":12,"area":null},{"id":"2107.02493","title":"Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting","created":"2021-07-06","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":"2409.04979","title":"RCBEVDet++: Toward High-accuracy Radar-Camera Fusion 3D Perception Network","created":"2024-09-08","cited_by_count":11,"area":null},{"id":"2102.03602","title":"Gated3D: Monocular 3D Object Detection From Temporal Illumination Cues","created":"2021-02-06","cited_by_count":10,"area":null},{"id":"2105.00268","title":"Lite-FPN for Keypoint-based Monocular 3D Object Detection","created":"2021-05-01","cited_by_count":10,"area":null},{"id":"2209.13507","title":"CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection","created":"2022-09-27","cited_by_count":10,"area":null},{"id":"2306.01738","title":"OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detection","created":"2023-06-02","cited_by_count":10,"area":null},{"id":"2206.03666","title":"Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking","created":"2022-06-08","cited_by_count":9,"area":null},{"id":"2303.13561","title":"MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation","created":"2023-03-23","cited_by_count":9,"area":null},{"id":"2305.07270","title":"SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detection","created":"2023-05-12","cited_by_count":9,"area":null},{"id":"2104.06041","title":"OCM3D: Object-Centric Monocular 3D Object Detection","created":"2021-04-13","cited_by_count":8,"area":null},{"id":"2305.03724","title":"DualCross: Cross-Modality Cross-Domain Adaptation for Monocular BEV Perception","created":"2023-05-05","cited_by_count":8,"area":null},{"id":"2210.16574","title":"Boosting Monocular 3D Object Detection with Object-Centric Auxiliary Depth Supervision","created":"2022-10-29","cited_by_count":7,"area":null},{"id":"2107.13279","title":"Pseudo-LiDAR Based Road Detection","created":"2021-07-28","cited_by_count":6,"area":null},{"id":"2205.11664","title":"Towards Model Generalization for Monocular 3D Object Detection","created":"2022-05-23","cited_by_count":6,"area":null},{"id":"2209.08459","title":"StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2310.00920","title":"Every Dataset Counts: Scaling up Monocular 3D Object Detection with Joint Datasets Training","created":"2023-10-02","cited_by_count":5,"area":null},{"id":"2310.15624","title":"GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2210.02493","title":"Depth Is All You Need for Monocular 3D Detection","created":"2022-10-05","cited_by_count":4,"area":null},{"id":"2506.03834","title":"CARE: Enhancing Safety of Visual Navigation through Collision Avoidance via Repulsive Estimation","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2103.03977","title":"Sparse LiDAR and Stereo Fusion (SLS-Fusion) for Depth Estimationand 3D Object Detection","created":"2021-03-05","cited_by_count":3,"area":null},{"id":"2107.13269","title":"Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth","created":"2021-07-28","cited_by_count":3,"area":null},{"id":"2111.12643","title":"SM3D: Simultaneous Monocular Mapping and 3D Detection","created":"2021-11-24","cited_by_count":3,"area":null},{"id":"2201.09354","title":"Survey and Systematization of 3D Object Detection Models and Methods","created":"2022-01-23","cited_by_count":3,"area":null},{"id":"2203.04538","title":"Monocular Depth Distribution Alignment with Low Computation","created":"2022-03-09","cited_by_count":3,"area":null},{"id":"2203.11018","title":"Stereo Neural Vernier Caliper","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2207.07933","title":"Consistency of Implicit and Explicit Features Matters for Monocular 3D Object Detection","created":"2022-07-16","cited_by_count":3,"area":null},{"id":"2303.05203","title":"RMMDet: Road-Side Multitype and Multigroup Sensor Detection System for Autonomous Driving","created":"2023-03-09","cited_by_count":3,"area":null},{"id":"2506.09541","title":"3DGeoDet: General-purpose Geometry-aware Image-based 3D Object Detection","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2207.02013","title":"Multiview Detection with Cardboard Human Modeling","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2208.07137","title":"An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detection","created":"2022-08-15","cited_by_count":2,"area":null},{"id":"2209.01567","title":"Pseudo-LiDAR for Visual Odometry","created":"2022-09-04","cited_by_count":2,"area":null},{"id":"2302.13002","title":"Introducing Depth into Transformer-based 3D Object Detection","created":"2023-02-25","cited_by_count":2,"area":null},{"id":"2309.09855","title":"PseudoCal: Towards Initialisation-Free Deep Learning-Based Camera-LiDAR Self-Calibration","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2404.09431","title":"Vision Foundation Model Driven Foreground-Aware Pseudo-LiDAR Generation for Monocular 3D Object Detection","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2411.15657","title":"Training an Open-Vocabulary Monocular 3D Object Detection Model without 3D Data","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2501.09481","title":"MonoSOWA: Scalable monocular 3D Object detector Without human Annotations","created":"2025-01-16","cited_by_count":2,"area":null},{"id":"2510.15385","title":"FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2206.13858","title":"Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?","created":"2022-06-28","cited_by_count":1,"area":null},{"id":"2209.00961","title":"LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile Devices","created":"2022-09-02","cited_by_count":1,"area":null},{"id":"2303.11243","title":"Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection","created":"2023-03-20","cited_by_count":1,"area":null},{"id":"2309.13570","title":"Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset","created":"2023-09-24","cited_by_count":1,"area":null},{"id":"2310.05447","title":"Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2312.14606","title":"Explainable Multi-Camera 3D Object Detection with Transformer-Based Saliency Maps","created":"2023-12-22","cited_by_count":1,"area":null},{"id":"2501.03700","title":"AuxDepthNet: Real-Time Monocular 3D Object Detection with Depth-Sensitive Features","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2503.04154","title":"CA-W3D: Leveraging Context-Aware Knowledge for Weakly Supervised Monocular 3D Detection","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2604.01646","title":"MonoSAOD: Monocular 3D Object Detection with Sparsely Annotated Label","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2112.05534","title":"An Embarrassingly Pragmatic Introduction to Vision-based Autonomous Robots","created":"2021-11-15","cited_by_count":0,"area":null},{"id":"2201.04341","title":"MDS-Net: A Multi-scale Depth Stratification Based Monocular 3D Object Detection Algorithm","created":"2022-01-12","cited_by_count":0,"area":null},{"id":"2208.09446","title":"MonoSIM: Simulating Learning Behaviors of Heterogeneous Point Cloud Object Detectors for Monocular 3D Object Detection","created":"2022-08-19","cited_by_count":0,"area":null},{"id":"2209.09486","title":"Self-supervised 3D Object Detection from Monocular Pseudo-LiDAR","created":"2022-09-20","cited_by_count":0,"area":null},{"id":"2212.02755","title":"Objects as Spatio-Temporal 2.5D points","created":"2022-12-06","cited_by_count":0,"area":null},{"id":"2301.07301","title":"PTA-Det: Point Transformer Associating Point cloud and Image for 3D Object Detection","created":"2023-01-18","cited_by_count":0,"area":null},{"id":"2306.10921","title":"Understanding Depth Map Progressively: Adaptive Distance Interval Separation for Monocular 3d Object Detection","created":"2023-06-19","cited_by_count":0,"area":null}],"next_cursor":"100"}