{"total":105,"rows":[{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329,"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":"2101.02691","title":"Self-Supervised Pretraining of 3D Features on any Point-Cloud","created":"2021-01-07","cited_by_count":217,"area":null},{"id":"2104.00678","title":"Group-Free 3D Object Detection via Transformers","created":"2021-04-01","cited_by_count":215,"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":"2106.05304","title":"Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline","created":"2021-06-09","cited_by_count":145,"area":null},{"id":"2103.02242","title":"FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation","created":"2021-03-03","cited_by_count":144,"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":"2105.11450","title":"SAT: 2D Semantics Assisted Training for 3D Visual Grounding","created":"2021-05-24","cited_by_count":124,"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":"2106.10823","title":"3D Object Detection for Autonomous Driving: A Survey","created":"2021-06-21","cited_by_count":106,"area":null},{"id":"2205.05740","title":"Surface Representation for Point Clouds","created":"2022-05-11","cited_by_count":84,"area":null},{"id":"2103.07466","title":"3D Semantic Scene Completion: a Survey","created":"2021-03-12","cited_by_count":74,"area":null},{"id":"2108.08755","title":"Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networks","created":"2021-08-19","cited_by_count":69,"area":null},{"id":"2104.06114","title":"Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds","created":"2021-04-13","cited_by_count":67,"area":null},{"id":"2302.05438","title":"Deep Learning on Implicit Neural Representations of Shapes","created":"2023-02-10","cited_by_count":63,"area":null},{"id":"2104.11225","title":"Pri3D: Can 3D Priors Help 2D Representation Learning?","created":"2021-04-22","cited_by_count":61,"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":"2104.03640","title":"Semantic Scene Completion via Integrating Instances and Scene in-the-Loop","created":"2021-04-08","cited_by_count":55,"area":null},{"id":"2112.02990","title":"4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding","created":"2021-12-06","cited_by_count":54,"area":null},{"id":"2206.10965","title":"Polar Parametrization for Vision-based Surround-View 3D Detection","created":"2022-06-22","cited_by_count":53,"area":null},{"id":"2303.08129","title":"PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection","created":"2023-03-14","cited_by_count":53,"area":null},{"id":"2201.01976","title":"SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection","created":"2022-01-06","cited_by_count":52,"area":null},{"id":"2112.11088","title":"EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection","created":"2021-12-21","cited_by_count":49,"area":null},{"id":"2211.11646","title":"NeRF-RPN: A general framework for object detection in NeRFs","created":"2022-11-21","cited_by_count":46,"area":null},{"id":"2101.06784","title":"Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving","created":"2021-01-17","cited_by_count":45,"area":null},{"id":"2204.02251","title":"RBGNet: Ray-based Grouping for 3D Object Detection","created":"2022-04-05","cited_by_count":40,"area":null},{"id":"2112.00236","title":"VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusion","created":"2021-12-01","cited_by_count":38,"area":null},{"id":"2108.07794","title":"RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection","created":"2021-08-17","cited_by_count":37,"area":null},{"id":"2105.06461","title":"3D Spatial Recognition without Spatially Labeled 3D","created":"2021-05-13","cited_by_count":31,"area":null},{"id":"2210.06036","title":"Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics","created":"2022-10-12","cited_by_count":30,"area":null},{"id":"2109.05566","title":"PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds","created":"2021-09-12","cited_by_count":26,"area":null},{"id":"2204.09848","title":"Weakly Aligned Feature Fusion for Multimodal Object Detection","created":"2022-04-21","cited_by_count":26,"area":null},{"id":"2406.05785","title":"A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions","created":"2024-06-09","cited_by_count":25,"area":null},{"id":"2207.04997","title":"A Closer Look at Invariances in Self-supervised Pre-training for 3D Vision","created":"2022-07-11","cited_by_count":24,"area":null},{"id":"2108.10165","title":"ODAM: Object Detection, Association, and Mapping using Posed RGB Video","created":"2021-08-23","cited_by_count":22,"area":null},{"id":"2203.14531","title":"Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimation","created":"2022-03-28","cited_by_count":22,"area":null},{"id":"2210.12755","title":"LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers","created":"2022-10-23","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":"2210.01391","title":"Bridged Transformer for Vision and Point Cloud 3D Object Detection","created":"2022-10-04","cited_by_count":20,"area":null},{"id":"2103.07969","title":"Monte Carlo Scene Search for 3D Scene Understanding","created":"2021-03-14","cited_by_count":19,"area":null},{"id":"2105.03211","title":"NeRD: Neural 3D Reflection Symmetry Detector","created":"2021-04-19","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":"2204.11911","title":"DArch: Dental Arch Prior-assisted 3D Tooth Instance Segmentation","created":"2022-04-25","cited_by_count":18,"area":null},{"id":"2203.05238","title":"Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement","created":"2022-03-10","cited_by_count":17,"area":null},{"id":"2208.09801","title":"PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition","created":"2022-08-21","cited_by_count":16,"area":null},{"id":"2204.05599","title":"HyperDet3D: Learning a Scene-conditioned 3D Object Detector","created":"2022-04-12","cited_by_count":14,"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":"2210.05593","title":"Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection","created":"2022-10-11","cited_by_count":14,"area":null},{"id":"2210.10138","title":"Class-Level Confidence Based 3D Semi-Supervised Learning","created":"2022-10-18","cited_by_count":14,"area":null},{"id":"2306.03206","title":"MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences","created":"2023-06-05","cited_by_count":13,"area":null},{"id":"2212.09948","title":"MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency","created":"2022-12-20","cited_by_count":12,"area":null},{"id":"2107.01205","title":"HandVoxNet++: 3D Hand Shape and Pose Estimation using Voxel-Based Neural Networks","created":"2021-07-02","cited_by_count":11,"area":null},{"id":"2207.10589","title":"Boosting 3D Object Detection via Object-Focused Image Fusion","created":"2022-07-21","cited_by_count":11,"area":null},{"id":"2210.15365","title":"Li3DeTr: A LiDAR based 3D Detection Transformer","created":"2022-10-27","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":"2107.11010","title":"3D Brain Reconstruction by Hierarchical Shape-Perception Network from a Single Incomplete Image","created":"2021-07-23","cited_by_count":10,"area":null},{"id":"2108.07378","title":"PnP-3D: A Plug-and-Play for 3D Point Clouds","created":"2021-08-16","cited_by_count":10,"area":null},{"id":"2201.08812","title":"DeepMix: Mobility-aware, Lightweight, and Hybrid 3D Object Detection for Headsets","created":"2022-01-15","cited_by_count":10,"area":null},{"id":"2403.07469","title":"A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes","created":"2024-03-12","cited_by_count":10,"area":null},{"id":"2112.02091","title":"Class-agnostic Reconstruction of Dynamic Objects from Videos","created":"2021-12-03","cited_by_count":8,"area":null},{"id":"2201.05816","title":"A Critical Analysis of Image-based Camera Pose Estimation Techniques","created":"2022-01-15","cited_by_count":7,"area":null},{"id":"2406.08152","title":"CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer","created":"2024-06-12","cited_by_count":7,"area":null},{"id":"2407.13748","title":"General Geometry-aware Weakly Supervised 3D Object Detection","created":"2024-07-18","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":"2110.04450","title":"Scene Editing as Teleoperation: A Case Study in 6DoF Kit Assembly","created":"2021-10-09","cited_by_count":6,"area":null},{"id":"2210.12513","title":"Learning Point-Language Hierarchical Alignment for 3D Visual Grounding","created":"2022-10-22","cited_by_count":6,"area":null},{"id":"2410.01404","title":"Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detection","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2108.12863","title":"MBDF-Net: Multi-Branch Deep Fusion Network for 3D Object Detection","created":"2021-08-29","cited_by_count":5,"area":null},{"id":"2203.13090","title":"AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception","created":"2022-03-24","cited_by_count":5,"area":null},{"id":"2211.01664","title":"PointSee: Image Enhances Point Cloud","created":"2022-11-03","cited_by_count":5,"area":null},{"id":"2111.07248","title":"Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation","created":"2021-11-14","cited_by_count":4,"area":null},{"id":"2404.00524","title":"TexVocab: Texture Vocabulary-conditioned Human Avatars","created":"2024-03-31","cited_by_count":4,"area":null},{"id":"2107.08392","title":"Dynamic Convolution for 3D Point Cloud Instance Segmentation","created":"2021-07-18","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":"2203.01152","title":"DisARM: Displacement Aware Relation Module for 3D Detection","created":"2022-03-02","cited_by_count":3,"area":null},{"id":"2203.06585","title":"CVFNet: Real-time 3D Object Detection by Learning Cross View Features","created":"2022-03-13","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":"2310.05346","title":"Anyview: Generalizable Indoor 3D Object Detection with Variable Frames","created":"2023-10-09","cited_by_count":3,"area":null},{"id":"2203.01449","title":"Object Pose Estimation using Mid-level Visual Representations","created":"2022-03-02","cited_by_count":2,"area":null},{"id":"2203.10456","title":"simCrossTrans: A Simple Cross-Modality Transfer Learning for Object Detection with ConvNets or Vision Transformers","created":"2022-03-20","cited_by_count":2,"area":null},{"id":"2205.02102","title":"Concept Activation Vectors for Generating User-Defined 3D Shapes","created":"2022-04-29","cited_by_count":2,"area":null},{"id":"2211.00382","title":"Seg&Struct: The Interplay Between Part Segmentation and Structure Inference for 3D Shape Parsing","created":"2022-11-01","cited_by_count":2,"area":null},{"id":"2301.04613","title":"Object Detection in 3D Point Clouds via Local Correlation-Aware Point Embedding","created":"2023-01-11","cited_by_count":2,"area":null},{"id":"2401.17058","title":"Atlanta Scaled layouts from non-central panoramas","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2506.08777","title":"Gaussian2Scene: 3D Scene Representation Learning via Self-supervised Learning with 3D Gaussian Splatting","created":"2025-06-10","cited_by_count":2,"area":null},{"id":"2508.17439","title":"Investigating Domain Gaps for Indoor 3D Object Detection","created":"2025-08-24","cited_by_count":2,"area":null},{"id":"2103.05401","title":"Deep 6-DoF Tracking of Unknown Objects for Reactive Grasping","created":"2021-03-09","cited_by_count":1,"area":null},{"id":"2310.02532","title":"ShaSTA-Fuse: Camera-LiDAR Sensor Fusion to Model Shape and Spatio-Temporal Affinities for 3D Multi-Object Tracking","created":"2023-10-04","cited_by_count":1,"area":null},{"id":"2311.06043","title":"Deep learning for 3D Object Detection and Tracking in Autonomous Driving: A Brief Survey","created":"2023-11-10","cited_by_count":1,"area":null},{"id":"2103.08294","title":"3D-FFS: Faster 3D object detection with Focused Frustum Search in sensor fusion based networks","created":"2021-03-15","cited_by_count":0,"area":null},{"id":"2105.09544","title":"Egocentric Activity Recognition and Localization on a 3D Map","created":"2021-05-20","cited_by_count":0,"area":null},{"id":"2205.12519","title":"Structure Aware and Class Balanced 3D Object Detection on nuScenes Dataset","created":"2022-05-25","cited_by_count":0,"area":null},{"id":"2208.14796","title":"3DLG-Detector: 3D Object Detection via Simultaneous Local-Global Feature Learning","created":"2022-08-31","cited_by_count":0,"area":null},{"id":"2211.07108","title":"Recursive Cross-View: Use Only 2D Detectors to Achieve 3D Object Detection without 3D Annotations","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2211.09518","title":"ImLiDAR: Cross-Sensor Dynamic Message Propagation Network for 3D Object Detection","created":"2022-11-17","cited_by_count":0,"area":null},{"id":"2212.01920","title":"Review on 6D Object Pose Estimation with the focus on Indoor Scene Understanding","created":"2022-12-04","cited_by_count":0,"area":null},{"id":"2212.05560","title":"Context-aware 6D Pose Estimation of Known Objects using RGB-D data","created":"2022-12-11","cited_by_count":0,"area":null},{"id":"2302.06291","title":"Surface-biased Multi-Level Context 3D Object Detection","created":"2023-02-13","cited_by_count":0,"area":null},{"id":"2305.12646","title":"SG-GAN: Fine Stereoscopic-Aware Generation for 3D Brain Point Cloud Up-sampling from a Single Image","created":"2023-05-22","cited_by_count":0,"area":null}],"next_cursor":"100"}