{"total":487,"rows":[{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179,"area":null},{"id":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","cited_by_count":110,"area":null},{"id":"2411.07184","title":"SAMPart3D: Segment Any Part in 3D Objects","created":"2024-11-11","cited_by_count":97,"area":null},{"id":"2410.18956","title":"Large Spatial Model: End-to-end Unposed Images to Semantic 3D","created":"2024-10-24","cited_by_count":73,"area":null},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65,"area":null},{"id":"2502.16652","title":"Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration","created":"2025-02-23","cited_by_count":51,"area":null},{"id":"2510.23607","title":"Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations","created":"2025-10-27","cited_by_count":45,"area":null},{"id":"2403.14418","title":"OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation","created":"2024-03-21","cited_by_count":44,"area":null},{"id":"2406.06526","title":"Generative Gaussian Splatting for Unbounded 3D City Generation","created":"2024-06-10","cited_by_count":44,"area":null},{"id":"2410.08114","title":"Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning","created":"2024-10-10","cited_by_count":43,"area":null},{"id":"2509.06784","title":"P3-SAM: Native 3D Part Segmentation","created":"2025-09-08","cited_by_count":43,"area":null},{"id":"2410.01345","title":"Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy","created":"2024-10-02","cited_by_count":38,"area":null},{"id":"2411.13550","title":"Find Any Part in 3D","created":"2024-11-20","cited_by_count":32,"area":null},{"id":"2507.13097","title":"GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training","created":"2025-07-17","cited_by_count":32,"area":null},{"id":"2503.18944","title":"DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation","created":"2025-03-24","cited_by_count":31,"area":null},{"id":"2412.12617","title":"PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection","created":"2024-12-17","cited_by_count":30,"area":null},{"id":"2503.02579","title":"MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments","created":"2025-03-04","cited_by_count":28,"area":null},{"id":"2506.03642","title":"Spatial Understanding from Videos: Structured Prompts Meet Simulation Data","created":"2025-06-04","cited_by_count":28,"area":null},{"id":"2403.09639","title":"GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding","created":"2024-03-14","cited_by_count":26,"area":null},{"id":"2506.15680","title":"Particle-Grid Neural Dynamics for Learning Deformable Object Models from RGB-D Videos","created":"2025-06-18","cited_by_count":25,"area":null},{"id":"2512.24766","title":"Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow","created":"2025-12-31","cited_by_count":25,"area":null},{"id":"2408.08753","title":"PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders","created":"2024-08-16","cited_by_count":24,"area":null},{"id":"2407.07995","title":"Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation","created":"2024-07-10","cited_by_count":23,"area":null},{"id":"2408.05020","title":"RadarPillars: Efficient Object Detection from 4D Radar Point Clouds","created":"2024-08-09","cited_by_count":23,"area":null},{"id":"2504.14151","title":"Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D","created":"2025-04-19","cited_by_count":23,"area":null},{"id":"2502.17019","title":"Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems","created":"2025-02-24","cited_by_count":22,"area":null},{"id":"2405.15214","title":"PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning","created":"2024-05-24","cited_by_count":21,"area":null},{"id":"2603.03283","title":"Utonia: Toward One Encoder for All Point Clouds","created":"2026-03-03","cited_by_count":21,"area":null},{"id":"2410.22489","title":"Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation","created":"2024-10-29","cited_by_count":20,"area":null},{"id":"2511.20343","title":"AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend","created":"2025-11-25","cited_by_count":20,"area":null},{"id":"2412.06234","title":"Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction","created":"2024-12-09","cited_by_count":18,"area":null},{"id":"2410.17505","title":"PLGS: Robust Panoptic Lifting with 3D Gaussian Splatting","created":"2024-10-23","cited_by_count":17,"area":null},{"id":"2512.13689","title":"LitePT: Lighter Yet Stronger Point Transformer","created":"2025-12-15","cited_by_count":17,"area":null},{"id":"2409.06322","title":"G3PT: Unleash the power of Autoregressive Modeling in 3D Generation via Cross-scale Querying Transformer","created":"2024-09-10","cited_by_count":16,"area":null},{"id":"2410.03644","title":"Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need","created":"2024-10-04","cited_by_count":16,"area":null},{"id":"2411.06390","title":"SplatFormer: Point Transformer for Robust 3D Gaussian Splatting","created":"2024-11-10","cited_by_count":16,"area":null},{"id":"2506.08710","title":"SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting","created":"2025-06-10","cited_by_count":15,"area":null},{"id":"2510.08575","title":"ReSplat: Learning Recurrent Gaussian Splatting","created":"2025-10-09","cited_by_count":15,"area":null},{"id":"2506.05282","title":"Rectified Point Flow: Generic Point Cloud Pose Estimation","created":"2025-06-05","cited_by_count":14,"area":null},{"id":"2409.18788","title":"Excavating in the Wild: The GOOSE-Ex Dataset for Semantic Segmentation","created":"2024-09-27","cited_by_count":13,"area":null},{"id":"2504.05400","title":"GARF: Learning Generalizable 3D Reassembly for Real-World Fractures","created":"2025-04-07","cited_by_count":13,"area":null},{"id":"2506.09784","title":"Accurate and efficient zero-shot 6D pose estimation with frozen foundation models","created":"2025-06-11","cited_by_count":13,"area":null},{"id":"2402.12535","title":"Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics","created":"2024-02-19","cited_by_count":12,"area":null},{"id":"2404.12794","title":"MambaMOS: LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Model","created":"2024-04-19","cited_by_count":12,"area":null},{"id":"2505.04965","title":"DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Grounding","created":"2025-05-08","cited_by_count":12,"area":null},{"id":"2412.07360","title":"Efficient 3D Recognition with Event-driven Spike Sparse Convolution","created":"2024-12-10","cited_by_count":11,"area":null},{"id":"2501.08286","title":"VINGS-Mono: Visual-Inertial Gaussian Splatting Monocular SLAM in Large Scenes","created":"2025-01-14","cited_by_count":11,"area":null},{"id":"2505.24287","title":"EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2507.17657","title":"Attention (as Discrete-Time Markov) Chains","created":"2025-07-23","cited_by_count":11,"area":null},{"id":"2404.10699","title":"ECLAIR: A High-Fidelity Aerial LiDAR Dataset for Semantic Segmentation","created":"2024-04-16","cited_by_count":10,"area":null},{"id":"2512.17817","title":"Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding","created":"2025-12-19","cited_by_count":10,"area":null},{"id":"2603.16869","title":"SegviGen: Repurposing 3D Generative Model for Part Segmentation","created":"2026-03-17","cited_by_count":10,"area":null},{"id":"2403.13188","title":"Reflectivity Is All You Need!: Advancing LiDAR Semantic Segmentation","created":"2024-03-19","cited_by_count":9,"area":null},{"id":"2408.06832","title":"FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving","created":"2024-08-13","cited_by_count":9,"area":null},{"id":"2411.19774","title":"PerLA: Perceptive 3D Language Assistant","created":"2024-11-29","cited_by_count":9,"area":null},{"id":"2503.03299","title":"Label-Efficient LiDAR Semantic Segmentation with 2D-3D Vision Transformer Adapters","created":"2025-03-05","cited_by_count":9,"area":null},{"id":"2503.10624","title":"ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2506.18882","title":"Light of Normals: Unified Feature Representation for Universal Photometric Stereo","created":"2025-06-23","cited_by_count":9,"area":null},{"id":"2510.05613","title":"PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction","created":"2025-10-07","cited_by_count":9,"area":null},{"id":"2410.07472","title":"Exploring the design space of deep-learning-based weather forecasting systems","created":"2024-10-09","cited_by_count":8,"area":null},{"id":"2411.19860","title":"SpaRC: Sparse Radar-Camera Fusion for 3D Object Detection","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2503.07940","title":"BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes","created":"2025-03-11","cited_by_count":8,"area":null},{"id":"2503.08140","title":"HOTFormerLoc: Hierarchical Octree Transformer for Versatile Lidar Place Recognition Across Ground and Aerial Views","created":"2025-03-11","cited_by_count":8,"area":null},{"id":"2503.24009","title":"Learning 3D-Gaussian Simulators from RGB Videos","created":"2025-03-31","cited_by_count":8,"area":null},{"id":"2505.21483","title":"MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2512.14364","title":"Unified Semantic Transformer for 3D Scene Understanding","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2603.01142","title":"ArtLLM: Generating Articulated Assets via 3D LLM","created":"2026-03-01","cited_by_count":8,"area":null},{"id":"2604.07053","title":"AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors","created":"2026-04-08","cited_by_count":8,"area":null},{"id":"2407.08260","title":"SALSA: Swift Adaptive Lightweight Self-Attention for Enhanced LiDAR Place Recognition","created":"2024-07-11","cited_by_count":7,"area":null},{"id":"2408.13802","title":"TripleMixer: A 3D Point Cloud Denoising Model for Adverse Weather","created":"2024-08-25","cited_by_count":7,"area":null},{"id":"2410.13924","title":"ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding","created":"2024-10-17","cited_by_count":7,"area":null},{"id":"2502.06227","title":"Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point clouds","created":"2025-02-10","cited_by_count":7,"area":null},{"id":"2502.20316","title":"Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Clouds","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2509.01250","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","created":"2025-09-01","cited_by_count":7,"area":null},{"id":"2411.02104","title":"Deep Learning on 3D Semantic Segmentation: A Detailed Review","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2503.08512","title":"SAS: Segment Any 3D Scene with Integrated 2D Priors","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2506.02112","title":"SAB3R: Semantic-Augmented Backbone in 3D Reconstruction","created":"2025-06-02","cited_by_count":6,"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":"2510.14146","title":"PoissonNet: A Local-Global Approach for Learning on Surfaces","created":"2025-10-15","cited_by_count":6,"area":null},{"id":"2512.00877","title":"Feed-Forward 3D Gaussian Splatting Compression with Long-Context Modeling","created":"2025-11-30","cited_by_count":6,"area":null},{"id":"2601.02457","title":"PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding","created":"2026-01-05","cited_by_count":6,"area":null},{"id":"2602.00148","title":"Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2603.23502","title":"OccAny: Generalized Unconstrained Urban 3D Occupancy","created":"2026-03-24","cited_by_count":6,"area":null},{"id":"2405.01882","title":"Millimeter Wave Radar-based Human Activity Recognition for Healthcare Monitoring Robot","created":"2024-05-03","cited_by_count":5,"area":null},{"id":"2405.18033","title":"RT-GS2: Real-Time Generalizable Semantic Segmentation for 3D Gaussian Representations of Radiance Fields","created":"2024-05-28","cited_by_count":5,"area":null},{"id":"2406.09126","title":"3D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2502.19247","title":"ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Grounding","created":"2025-02-26","cited_by_count":5,"area":null},{"id":"2503.12539","title":"BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis","created":"2025-03-16","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":"2511.13115","title":"A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Features","created":"2025-11-17","cited_by_count":5,"area":null},{"id":"2601.05237","title":"ObjectForesight: Predicting Future 3D Object Trajectories from Human Videos","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2602.14193","title":"Learning Part-Aware Dense 3D Feature Field for Generalizable Articulated Object Manipulation","created":"2026-02-15","cited_by_count":5,"area":null},{"id":"2410.10510","title":"Exploiting Local Features and Range Images for Small Data Real-Time Point Cloud Semantic Segmentation","created":"2024-10-14","cited_by_count":4,"area":null},{"id":"2412.07377","title":"CADSpotting: Robust Panoptic Symbol Spotting on Large-Scale CAD Drawings","created":"2024-12-10","cited_by_count":4,"area":null},{"id":"2501.06785","title":"3DCoMPaT200: Language-Grounded Compositional Understanding of Parts and Materials of 3D Shapes","created":"2025-01-12","cited_by_count":4,"area":null},{"id":"2503.08352","title":"Mitigating Ambiguities in 3D Classification with Gaussian Splatting","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2503.10055","title":"Fourier Decomposition for Explicit Representation of 3D Point Cloud Attributes","created":"2025-03-13","cited_by_count":4,"area":null},{"id":"2503.15106","title":"Distilling 3D distinctive local descriptors for 6D pose estimation","created":"2025-03-19","cited_by_count":4,"area":null},{"id":"2503.23980","title":"SALT: A Flexible Semi-Automatic Labeling Tool for General LiDAR Point Clouds with Cross-Scene Adaptability and 4D Consistency","created":"2025-03-31","cited_by_count":4,"area":null},{"id":"2504.01483","title":"GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling","created":"2025-04-02","cited_by_count":4,"area":null}],"next_cursor":"100"}