{"total":97,"rows":[{"id":"2304.14365","title":"Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving","created":"2023-04-27","cited_by_count":332,"area":"wm"},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303,"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":"2304.06906","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","created":"2023-04-14","cited_by_count":113,"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":"2311.14405","title":"OneFormer3D: One Transformer for Unified Point Cloud Segmentation","created":"2023-11-24","cited_by_count":95,"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":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65,"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":"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":"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":"2201.00785","title":"Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning","created":"2022-01-03","cited_by_count":46,"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":"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":"2412.04380","title":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding","created":"2024-12-05","cited_by_count":45,"area":null},{"id":"2412.04458","title":"Cubify Anything: Scaling Indoor 3D Object Detection","created":"2024-12-05","cited_by_count":39,"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":"2302.02871","title":"Top-Down Beats Bottom-Up in 3D Instance Segmentation","created":"2023-02-06","cited_by_count":31,"area":null},{"id":"2310.05699","title":"Uni3DETR: Unified 3D Detection Transformer","created":"2023-10-09","cited_by_count":27,"area":null},{"id":"2311.02684","title":"Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE","created":"2023-11-05","cited_by_count":25,"area":"moe"},{"id":"2402.03327","title":"Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models","created":"2024-01-09","cited_by_count":25,"area":null},{"id":"2404.01300","title":"NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields","created":"2024-04-01","cited_by_count":20,"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":"2502.10392","title":"TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding","created":"2025-02-14","cited_by_count":17,"area":null},{"id":"2304.13031","title":"DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection","created":"2023-04-25","cited_by_count":16,"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":"2305.19623","title":"Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast","created":"2023-05-31","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":"2312.02966","title":"Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection","created":"2023-12-05","cited_by_count":14,"area":"diffusion"},{"id":"2304.06911","title":"3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining","created":"2023-04-14","cited_by_count":13,"area":null},{"id":"2403.06974","title":"Memory-based Adapters for Online 3D Scene Perception","created":"2024-03-11","cited_by_count":13,"area":null},{"id":"2410.01647","title":"3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for Indoor 3D Object Detection","created":"2024-10-02","cited_by_count":13,"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":"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":"2411.14869","title":"BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence","created":"2024-11-22","cited_by_count":10,"area":null},{"id":"2403.15019","title":"BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation","created":"2024-03-22","cited_by_count":9,"area":null},{"id":"2603.00912","title":"VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection","created":"2026-03-01","cited_by_count":9,"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":"2403.04198","title":"CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoors Object Detection from Multi-view Images","created":"2024-03-07","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":"2210.07424","title":"Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction","created":"2022-10-13","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":"2307.13251","title":"GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers","created":"2023-07-25","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":"2402.14215","title":"Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understanding","created":"2024-02-22","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":"2312.12418","title":"LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset","created":"2023-12-19","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":"2402.14464","title":"NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detection","created":"2024-02-22","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":"2506.05199","title":"DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2511.20253","title":"Zoo3D: Zero-Shot 3D Object Detection at Scene Level","created":"2025-11-25","cited_by_count":4,"area":null},{"id":"2211.07084","title":"Boosting Semi-Supervised 3D Object Detection with Semi-Sampling","created":"2022-11-14","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":"2404.06044","title":"Object Dynamics Modeling with Hierarchical Point Cloud-based Representations","created":"2024-04-09","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":"2506.15610","title":"BoxFusion: Reconstruction-Free Open-Vocabulary 3D Object Detection via Real-Time Multi-View Box Fusion","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2207.03720","title":"Bounding Box Disparity: 3D Metrics for Object Detection With Full Degree of Freedom","created":"2022-07-08","cited_by_count":2,"area":null},{"id":"2304.00961","title":"Self-Ordering Point Clouds","created":"2023-04-03","cited_by_count":2,"area":null},{"id":"2404.13921","title":"NeRF-DetS: Enhanced Adaptive Spatial-wise Sampling and View-wise Fusion Strategies for NeRF-based Indoor Multi-view 3D Object Detection","created":"2024-04-22","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":"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":"2505.23756","title":"Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2510.17686","title":"Towards 3D Objectness Learning in an Open World","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2604.07997","title":"Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2303.07872","title":"Object-based SLAM utilizing unambiguous pose parameters considering general symmetry types","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2303.15493","title":"Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis","created":"2023-03-27","cited_by_count":1,"area":null},{"id":"2401.07477","title":"CascadeV-Det: Cascade Point Voting for 3D Object Detection","created":"2024-01-15","cited_by_count":1,"area":null},{"id":"2408.06604","title":"MV-DETR: Multi-modality indoor object detection by Multi-View DEtecton TRansformers","created":"2024-08-13","cited_by_count":1,"area":null},{"id":"2503.05127","title":"HexPlane Representation for 3D Semantic Scene Understanding","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2507.18331","title":"Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction","created":"2025-07-24","cited_by_count":1,"area":null},{"id":"2509.21388","title":"TUN3D: Towards Real-World Scene Understanding from Unposed Images","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2603.07985","title":"On the Feasibility and Opportunity of Autoregressive 3D Object Detection","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2604.10573","title":"Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2608.12179","title":"Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2404.00364","title":"Accurate Cutting-point Estimation for Robotic Lychee Harvesting through Geometry-aware Learning","created":"2024-03-30","cited_by_count":0,"area":null},{"id":"2512.01306","title":"Gaussian Swaying: Surface-Based Framework for Aerodynamic Simulation with 3D Gaussians","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2512.02991","title":"GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2601.22616","title":"UniGeo: A Unified 3D Indoor Object Detection Framework Integrating Geometry-Aware Learning and Dynamic Channel Gating","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.21944","title":"Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.16696","title":"LOD-Net: Locality-Aware 3D Object Detection Using Multi-Scale Transformer Network","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2607.06097","title":"PVCap: Towards Accurate 3D Dense Captioning via PseudoCap and VoxelCapNet","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.14560","title":"Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2609.19716","title":"GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.26702","title":"DIFTA-3D: Depth-Consistent Instance-Level Feature Transfer and Adaptation of DINOv3 for 3D Detection","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.31595","title":"GraphWrit3R: End-to-End 3D Scene Graph Writing","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.01283","title":"ShelfChange3D: Object-Level 3D Change Detection for Retail Shelf Monitoring","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}