{"total":46,"rows":[{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587,"area":null},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"area":null},{"id":"2303.04748","title":"CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP","created":"2023-03-08","cited_by_count":89,"area":null},{"id":"2310.08370","title":"UniPAD: A Universal Pre-training Paradigm for Autonomous Driving","created":"2023-10-12","cited_by_count":73,"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":"2402.02500","title":"Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning","created":"2024-02-04","cited_by_count":45,"area":null},{"id":"2311.17707","title":"SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation","created":"2023-11-29","cited_by_count":44,"area":null},{"id":"2403.07563","title":"Learning Generalizable Feature Fields for Mobile Manipulation","created":"2024-03-12","cited_by_count":31,"area":null},{"id":"2410.08208","title":"SPA: 3D Spatial-Awareness Enables Effective Embodied Representation","created":"2024-10-10","cited_by_count":28,"area":null},{"id":"2404.01491","title":"SUGAR: Pre-training 3D Visual Representations for Robotics","created":"2024-04-01","cited_by_count":26,"area":null},{"id":"2406.10224","title":"EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models","created":"2024-06-14","cited_by_count":26,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null},{"id":"2305.04691","title":"Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey","created":"2023-05-08","cited_by_count":21,"area":null},{"id":"2503.20168","title":"EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis","created":"2025-03-26","cited_by_count":21,"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":"2405.14959","title":"EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting","created":"2024-05-23","cited_by_count":20,"area":null},{"id":"2311.01734","title":"Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training","created":"2023-11-03","cited_by_count":18,"area":null},{"id":"2407.05862","title":"Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning","created":"2024-07-08","cited_by_count":16,"area":null},{"id":"2403.18922","title":"Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D","created":"2024-03-27","cited_by_count":15,"area":null},{"id":"2407.03263","title":"A Unified Framework for 3D Scene Understanding","created":"2024-07-03","cited_by_count":15,"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":"2408.11241","title":"CooPre: Cooperative Pretraining for V2X Cooperative Perception","created":"2024-08-20","cited_by_count":11,"area":null},{"id":"2502.17053","title":"PointSea: Point Cloud Completion via Self-structure Augmentation","created":"2025-02-24","cited_by_count":9,"area":null},{"id":"2403.08760","title":"MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning","created":"2024-03-13","cited_by_count":8,"area":null},{"id":"2311.04501","title":"PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds","created":"2023-11-08","cited_by_count":7,"area":null},{"id":"2401.12452","title":"Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration","created":"2024-01-23","cited_by_count":7,"area":null},{"id":"2407.12395","title":"Efficient Depth-Guided Urban View Synthesis","created":"2024-07-17","cited_by_count":7,"area":null},{"id":"2507.05260","title":"Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations","created":"2025-07-07","cited_by_count":7,"area":null},{"id":"2506.09952","title":"UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting","created":"2025-06-11","cited_by_count":6,"area":null},{"id":"2505.10105","title":"EmbodiedMAE: A Unified 3D Multi-Modal Representation for Robot Manipulation","created":"2025-05-15","cited_by_count":5,"area":null},{"id":"2601.15951","title":"EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesis","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2412.03054","title":"TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception","created":"2024-12-04","cited_by_count":2,"area":null},{"id":"2503.08422","title":"JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data","created":"2025-03-11","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":"2508.02172","title":"GaussianCross: Cross-modal Self-supervised 3D Representation Learning via Gaussian Splatting","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2508.08910","title":"Masked Clustering Prediction for Unsupervised Point Cloud Pre-training","created":"2025-08-12","cited_by_count":2,"area":null},{"id":"2509.13116","title":"Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Driving","created":"2025-09-16","cited_by_count":2,"area":null},{"id":"2405.17942","title":"Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perception","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2411.18667","title":"Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting","created":"2024-11-27","cited_by_count":1,"area":null},{"id":"2412.03059","title":"CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2510.24261","title":"DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2605.01759","title":"PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learning","created":"2026-05-03","cited_by_count":1,"area":null},{"id":"2605.21258","title":"Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.02268","title":"From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2503.07167","title":"Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2504.13788","title":"RefComp: A Reference-guided Unified Framework for Unpaired Point Cloud Completion","created":"2025-04-18","cited_by_count":0,"area":null}],"next_cursor":null}