{"total":120,"rows":[{"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":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329,"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":"2112.01554","title":"Neural Head Avatars from Monocular RGB Videos","created":"2021-12-02","cited_by_count":213,"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":"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":"2203.11183","title":"Masked Discrimination for Self-Supervised Learning on Point Clouds","created":"2022-03-21","cited_by_count":155,"area":null},{"id":"2204.08721","title":"Multimodal Token Fusion for Vision Transformers","created":"2022-04-19","cited_by_count":136,"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":"2305.03045","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","created":"2023-05-04","cited_by_count":109,"area":null},{"id":"2209.05588","title":"CenterFormer: Center-based Transformer for 3D Object Detection","created":"2022-09-12","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":"2205.05740","title":"Surface Representation for Point Clouds","created":"2022-05-11","cited_by_count":84,"area":null},{"id":"2303.12417","title":"CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data","created":"2023-03-22","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":"2104.11225","title":"Pri3D: Can 3D Priors Help 2D Representation Learning?","created":"2021-04-22","cited_by_count":61,"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":"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":"2112.02990","title":"4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding","created":"2021-12-06","cited_by_count":54,"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":"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":"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},{"id":"2301.00157","title":"Ponder: Point Cloud Pre-training via Neural Rendering","created":"2022-12-31","cited_by_count":50,"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":"2309.01692","title":"Mask-Attention-Free Transformer for 3D Instance Segmentation","created":"2023-09-04","cited_by_count":46,"area":null},{"id":"2303.14408","title":"VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud","created":"2023-03-25","cited_by_count":43,"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":"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":"2105.10620","title":"HPNet: Deep Primitive Segmentation Using Hybrid Representations","created":"2021-05-22","cited_by_count":36,"area":null},{"id":"2308.04409","title":"V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection","created":"2023-08-08","cited_by_count":35,"area":null},{"id":"2302.02858","title":"TR3D: Towards Real-Time Indoor 3D Object Detection","created":"2023-02-06","cited_by_count":32,"area":null},{"id":"2105.06461","title":"3D Spatial Recognition without Spatially Labeled 3D","created":"2021-05-13","cited_by_count":31,"area":null},{"id":"2108.13499","title":"Scene Synthesis via Uncertainty-Driven Attribute Synchronization","created":"2021-08-30","cited_by_count":29,"area":null},{"id":"2310.05699","title":"Uni3DETR: Unified 3D Detection Transformer","created":"2023-10-09","cited_by_count":27,"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":"2207.01987","title":"Open-Vocabulary 3D Detection via Image-level Class and Debiased Cross-modal Contrastive Learning","created":"2022-07-05","cited_by_count":23,"area":null},{"id":"2204.13630","title":"Rotationally Equivariant 3D Object Detection","created":"2022-04-28","cited_by_count":21,"area":null},{"id":"2208.04309","title":"3D Vision with Transformers: A Survey","created":"2022-08-08","cited_by_count":21,"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":"2210.01391","title":"Bridged Transformer for Vision and Point Cloud 3D Object Detection","created":"2022-10-04","cited_by_count":20,"area":null},{"id":"2409.04234","title":"UniDet3D: Multi-dataset Indoor 3D Object Detection","created":"2024-09-06","cited_by_count":20,"area":null},{"id":"2312.14465","title":"FM-OV3D: Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection","created":"2023-12-22","cited_by_count":19,"area":null},{"id":"2403.19580","title":"OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation","created":"2024-03-28","cited_by_count":19,"area":null},{"id":"2203.10856","title":"RGB-Depth Fusion GAN for Indoor Depth Completion","created":"2022-03-21","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":"2406.00830","title":"Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection","created":"2024-06-02","cited_by_count":17,"area":null},{"id":"2312.11112","title":"ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding","created":"2023-12-18","cited_by_count":16,"area":null},{"id":"2302.14746","title":"Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors","created":"2023-02-28","cited_by_count":15,"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":"2210.05593","title":"Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection","created":"2022-10-11","cited_by_count":14,"area":null},{"id":"2308.09098","title":"ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection","created":"2023-08-17","cited_by_count":14,"area":null},{"id":"2305.05026","title":"Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understanding","created":"2023-05-08","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":"2503.11081","title":"MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation","created":"2025-03-14","cited_by_count":12,"area":null},{"id":"2202.09715","title":"ARM3D: Attention-based relation module for indoor 3D object detection","created":"2022-02-20","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":"2312.13641","title":"SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection","created":"2023-12-21","cited_by_count":11,"area":null},{"id":"2404.15010","title":"X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition","created":"2024-04-23","cited_by_count":11,"area":null},{"id":"2203.09440","title":"TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenes","created":"2022-03-17","cited_by_count":10,"area":null},{"id":"2407.08931","title":"Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection","created":"2024-07-12","cited_by_count":10,"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":"2107.04013","title":"Multi-Modality Task Cascade for 3D Object Detection","created":"2021-07-08","cited_by_count":7,"area":null},{"id":"2302.05201","title":"PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysis","created":"2023-02-10","cited_by_count":7,"area":null},{"id":"2306.03584","title":"RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2403.15161","title":"FastCAD: Real-Time CAD Retrieval and Alignment from Scans and Videos","created":"2024-03-22","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":"2410.21566","title":"MVSDet: Multi-View Indoor 3D Object Detection via Efficient Plane Sweeps","created":"2024-10-28","cited_by_count":7,"area":null},{"id":"2508.20063","title":"OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations","created":"2025-08-27","cited_by_count":7,"area":null},{"id":"2604.05212","title":"Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D","created":"2026-04-06","cited_by_count":7,"area":null},{"id":"2203.10546","title":"Towards 3D Scene Understanding by Referring Synthetic Models","created":"2022-03-20","cited_by_count":6,"area":null},{"id":"2207.11753","title":"Label-Guided Auxiliary Training Improves 3D Object Detector","created":"2022-07-24","cited_by_count":6,"area":null},{"id":"2211.14091","title":"Language-Assisted 3D Feature Learning for Semantic Scene Understanding","created":"2022-11-25","cited_by_count":6,"area":null},{"id":"2312.08054","title":"Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequence","created":"2023-12-13","cited_by_count":6,"area":null},{"id":"2312.10390","title":"Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection","created":"2023-12-16","cited_by_count":6,"area":null},{"id":"2211.01664","title":"PointSee: Image Enhances Point Cloud","created":"2022-11-03","cited_by_count":5,"area":null},{"id":"2303.04458","title":"Full Point Encoding for Local Feature Aggregation in 3D Point Clouds","created":"2023-03-08","cited_by_count":5,"area":null},{"id":"2402.10002","title":"MM-Point: Multi-View Information-Enhanced Multi-Modal Self-Supervised 3D Point Cloud Understanding","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2404.02527","title":"Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2503.14493","title":"State Space Model Meets Transformer: A New Paradigm for 3D Object Detection","created":"2025-03-18","cited_by_count":5,"area":null},{"id":"2503.15211","title":"GO-N3RDet: Geometry Optimized NeRF-enhanced 3D Object Detector","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2305.03716","title":"3D Small Object Detection with Dynamic Spatial Pruning","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2505.16399","title":"Sketchy Bounding-box Supervision for 3D Instance Segmentation","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2509.21114","title":"CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2103.10042","title":"Suppress-and-Refine Framework for End-to-End 3D Object Detection","created":"2021-03-18","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":"2309.16956","title":"Model2Scene: Learning 3D Scene Representation via Contrastive Language-CAD Models Pre-training","created":"2023-09-29","cited_by_count":3,"area":null},{"id":"2310.06385","title":"3DS-SLAM: A 3D Object Detection based Semantic SLAM towards Dynamic Indoor Environments","created":"2023-10-10","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":"2503.10210","title":"TARS: Traffic-Aware Radar Scene Flow Estimation","created":"2025-03-13","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":"2211.01184","title":"Joint Data and Feature Augmentation for Self-Supervised Representation Learning on Point Clouds","created":"2022-11-02","cited_by_count":2,"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":"2309.11133","title":"Shape Anchor Guided Holistic Indoor Scene Understanding","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2406.11311","title":"Syn-to-Real Unsupervised Domain Adaptation for Indoor 3D Object Detection","created":"2024-06-17","cited_by_count":2,"area":null},{"id":"2504.03654","title":"PointSplit: Towards On-device 3D Object Detection with Heterogeneous Low-power Accelerators","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2108.06925","title":"Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks","created":"2021-08-16","cited_by_count":1,"area":null},{"id":"2202.09721","title":"3DRM:Pair-wise relation module for 3D object detection","created":"2022-02-20","cited_by_count":1,"area":null},{"id":"2407.05769","title":"Boosting 3D Object Detection with Semantic-Aware Multi-Branch Framework","created":"2024-07-08","cited_by_count":1,"area":null}],"next_cursor":"100"}