{"total":648,"rows":[{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575,"area":null},{"id":"2206.10092","title":"BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection","created":"2022-06-21","cited_by_count":572,"area":null},{"id":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466,"area":"wm"},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454,"area":null},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346,"area":null},{"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":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314,"area":"lr"},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303,"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":"2303.11301","title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","created":"2023-03-20","cited_by_count":222,"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":"2311.18651","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","created":"2023-11-30","cited_by_count":210,"area":"lr"},{"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":"2203.01509","title":"SoftGroup for 3D Instance Segmentation on Point Clouds","created":"2022-03-03","cited_by_count":200,"area":null},{"id":"2203.00680","title":"CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding","created":"2022-03-01","cited_by_count":198,"area":null},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197,"area":null},{"id":"2109.00179","title":"Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds","created":"2021-09-01","cited_by_count":180,"area":null},{"id":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175,"area":"lr"},{"id":"2111.06881","title":"Multimodal Virtual Point 3D Detection","created":"2021-11-12","cited_by_count":166,"area":null},{"id":"2103.14898","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","created":"2021-03-27","cited_by_count":163,"area":null},{"id":"2409.12961","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","created":"2024-09-19","cited_by_count":159,"area":null},{"id":"2106.01178","title":"ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection","created":"2021-06-02","cited_by_count":157,"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":"2203.11183","title":"Masked Discrimination for Self-Supervised Learning on Point Clouds","created":"2022-03-21","cited_by_count":155,"area":null},{"id":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147,"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":"2103.02242","title":"FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation","created":"2021-03-03","cited_by_count":144,"area":null},{"id":"2103.01128","title":"InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring","created":"2021-03-01","cited_by_count":141,"area":null},{"id":"2204.08721","title":"Multimodal Token Fusion for Vision Transformers","created":"2022-04-19","cited_by_count":136,"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":"2203.11139","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":"2308.08769","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","created":"2023-08-17","cited_by_count":129,"area":null},{"id":"2112.08879","title":"Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds","created":"2021-12-16","cited_by_count":128,"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":"2209.05324","title":"Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe","created":"2022-09-12","cited_by_count":122,"area":null},{"id":"2211.09646","title":"Language Conditioned Spatial Relation Reasoning for 3D Object Grounding","created":"2022-11-17","cited_by_count":122,"area":null},{"id":"2212.08320","title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?","created":"2022-12-16","cited_by_count":122,"area":"distill"},{"id":"2301.06051","title":"DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets","created":"2023-01-15","cited_by_count":122,"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":"2204.06272","title":"3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection","created":"2022-04-13","cited_by_count":110,"area":null},{"id":"2305.03045","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","created":"2023-05-04","cited_by_count":109,"area":null},{"id":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109,"area":"mllm"},{"id":"2103.14962","title":"Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation","created":"2021-03-27","cited_by_count":107,"area":null},{"id":"2107.02191","title":"TransformerFusion: Monocular RGB Scene Reconstruction using Transformers","created":"2021-07-05","cited_by_count":106,"area":null},{"id":"2112.04702","title":"Fast Point Transformer","created":"2021-12-09","cited_by_count":104,"area":null},{"id":"2103.06526","title":"DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency","created":"2021-03-11","cited_by_count":103,"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":"2209.14941","title":"EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding","created":"2022-09-29","cited_by_count":99,"area":null},{"id":"2112.00322","title":"FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection","created":"2021-12-01","cited_by_count":97,"area":null},{"id":"2403.13064","title":"SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model","created":"2024-03-19","cited_by_count":96,"area":null},{"id":"2311.14405","title":"OneFormer3D: One Transformer for Unified Point Cloud Segmentation","created":"2023-11-24","cited_by_count":95,"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":"2205.05740","title":"Surface Representation for Point Clouds","created":"2022-05-11","cited_by_count":84,"area":null},{"id":"2207.10035","title":"Fully Sparse 3D Object Detection","created":"2022-07-20","cited_by_count":84,"area":null},{"id":"2103.16381","title":"Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud","created":"2021-03-30","cited_by_count":81,"area":null},{"id":"2301.02508","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","created":"2023-01-06","cited_by_count":78,"area":null},{"id":"2103.07466","title":"3D Semantic Scene Completion: a Survey","created":"2021-03-12","cited_by_count":74,"area":null},{"id":"2106.04779","title":"Point Cloud Upsampling via Disentangled Refinement","created":"2021-06-09","cited_by_count":74,"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":"2505.04769","title":"Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges","created":"2025-05-07","cited_by_count":74,"area":"mllm"},{"id":"2203.00843","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","created":"2022-03-02","cited_by_count":70,"area":"distill"},{"id":"2212.00836","title":"UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding","created":"2022-12-01","cited_by_count":69,"area":null},{"id":"2205.13713","title":"PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences","created":"2022-05-27","cited_by_count":68,"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":"2112.04628","title":"Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection","created":"2021-12-09","cited_by_count":67,"area":null},{"id":"2108.04728","title":"Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds","created":"2021-08-10","cited_by_count":66,"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":"2112.02857","title":"PTTR: Relational 3D Point Cloud Object Tracking with Transformer","created":"2021-12-06","cited_by_count":65,"area":null},{"id":"2205.05979","title":"MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection","created":"2022-05-12","cited_by_count":65,"area":null},{"id":"2311.15383","title":"Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding","created":"2023-11-26","cited_by_count":64,"area":null},{"id":"2106.12735","title":"Multi-Modal 3D Object Detection in Autonomous Driving: a Survey","created":"2021-06-24","cited_by_count":63,"area":null},{"id":"2107.11355","title":"Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency","created":"2021-07-23","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":"2105.02158","title":"VoxelContext-Net: An Octree based Framework for Point Cloud Compression","created":"2021-05-05","cited_by_count":61,"area":null},{"id":"2112.09329","title":"Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders","created":"2021-12-17","cited_by_count":60,"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":"2210.04264","title":"CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds","created":"2022-10-09","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":"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":"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":"2310.08586","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","created":"2023-10-12","cited_by_count":56,"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":"2203.01730","title":"Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds","created":"2022-03-03","cited_by_count":55,"area":null},{"id":"2304.06061","title":"CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes","created":"2023-04-12","cited_by_count":55,"area":"mllm"},{"id":"2111.04426","title":"3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds","created":"2021-11-08","cited_by_count":54,"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":"2202.13589","title":"Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey","created":"2022-02-28","cited_by_count":54,"area":null},{"id":"2106.14193","title":"SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation","created":"2021-06-27","cited_by_count":53,"area":null},{"id":"2109.04310","title":"Deep Hough Voting for Robust Global Registration","created":"2021-09-09","cited_by_count":53,"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":"2112.01551","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding","created":"2021-12-02","cited_by_count":52,"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":"2310.02960","title":"CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection","created":"2023-10-04","cited_by_count":52,"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":"2307.14620","title":"NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection","created":"2023-07-27","cited_by_count":51,"area":null}],"next_cursor":"100"}