{"total":148,"rows":[{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429,"area":null},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365,"area":null},{"id":"2310.17596","title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","created":"2023-10-26","cited_by_count":327,"area":"offlinerl"},{"id":"2311.15260","title":"NeuRAD: Neural Rendering for Autonomous Driving","created":"2023-11-26","cited_by_count":150,"area":"driving"},{"id":"2401.11439","title":"General Flow as Foundation Affordance for Scalable Robot Learning","created":"2024-01-21","cited_by_count":85,"area":null},{"id":"2311.18448","title":"HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video","created":"2023-11-30","cited_by_count":78,"area":null},{"id":"2309.05663","title":"Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips","created":"2023-09-11","cited_by_count":74,"area":null},{"id":"2502.19459","title":"ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting","created":"2025-02-26","cited_by_count":67,"area":null},{"id":"2504.18904","title":"RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning","created":"2025-04-26","cited_by_count":54,"area":"offlinerl"},{"id":"2503.18673","title":"Any6D: Model-free 6D Pose Estimation of Novel Objects","created":"2025-03-24","cited_by_count":49,"area":null},{"id":"2308.01477","title":"HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions","created":"2023-08-02","cited_by_count":48,"area":null},{"id":"2404.12383","title":"G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis","created":"2024-04-18","cited_by_count":43,"area":"diffusion"},{"id":"2405.07801","title":"Deep Learning-Based Object Pose Estimation: A Comprehensive Survey","created":"2024-05-13","cited_by_count":40,"area":null},{"id":"2312.07063","title":"Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation","created":"2023-12-12","cited_by_count":38,"area":"diffusion"},{"id":"2507.00990","title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","created":"2025-07-01","cited_by_count":38,"area":null},{"id":"2607.05391","title":"LLM-as-a-Verifier: A General-Purpose Verification Framework","created":"2026-07-06","cited_by_count":30,"area":"lr"},{"id":"2312.00690","title":"Open-vocabulary object 6D pose estimation","created":"2023-12-01","cited_by_count":29,"area":null},{"id":"2406.06843","title":"HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction","created":"2024-06-10","cited_by_count":29,"area":null},{"id":"2312.13469","title":"Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation","created":"2023-12-20","cited_by_count":28,"area":null},{"id":"2404.06507","title":"Reconstructing Hand-Held Objects in 3D from Images and Videos","created":"2024-04-09","cited_by_count":24,"area":null},{"id":"2406.19811","title":"EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting","created":"2024-06-28","cited_by_count":23,"area":null},{"id":"2408.13953","title":"InterTrack: Tracking Human Object Interaction without Object Templates","created":"2024-08-25","cited_by_count":23,"area":null},{"id":"2410.20220","title":"Neural Fields in Robotics: A Survey","created":"2024-10-26","cited_by_count":21,"area":null},{"id":"2511.07416","title":"Robot Learning from a Physical World Model","created":"2025-11-10","cited_by_count":20,"area":"wm"},{"id":"2504.02812","title":"BOP Challenge 2024 on Model-Based and Model-Free 6D Object Pose Estimation","created":"2025-04-03","cited_by_count":19,"area":null},{"id":"2405.01333","title":"NeRFs in Robotics: A Survey","created":"2024-05-02","cited_by_count":16,"area":null},{"id":"2312.09138","title":"Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments","created":"2023-12-14","cited_by_count":15,"area":null},{"id":"2512.11988","title":"CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction","created":"2025-12-12","cited_by_count":14,"area":null},{"id":"2405.14045","title":"Learning rigid-body simulators over implicit shapes for large-scale scenes and vision","created":"2024-05-22","cited_by_count":12,"area":null},{"id":"2310.00463","title":"Diff-DOPE: Differentiable Deep Object Pose Estimation","created":"2023-09-30","cited_by_count":11,"area":null},{"id":"2412.01543","title":"6DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splatting","created":"2024-12-02","cited_by_count":11,"area":null},{"id":"2503.05578","title":"Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integration","created":"2025-03-07","cited_by_count":11,"area":null},{"id":"2503.21313","title":"HORT: Monocular Hand-held Objects Reconstruction with Transformers","created":"2025-03-27","cited_by_count":11,"area":null},{"id":"2401.04143","title":"RHOBIN Challenge: Reconstruction of Human Object Interaction","created":"2024-01-07","cited_by_count":10,"area":null},{"id":"2403.12396","title":"OV9D: Open-Vocabulary Category-Level 9D Object Pose and Size Estimation","created":"2024-03-19","cited_by_count":10,"area":"diffusion"},{"id":"2404.17906","title":"VIEW: Visual Imitation Learning with Waypoints","created":"2024-04-27","cited_by_count":10,"area":"offlinerl"},{"id":"2411.19162","title":"Lost & Found: Tracking Changes from Egocentric Observations in 3D Dynamic Scene Graphs","created":"2024-11-28","cited_by_count":10,"area":null},{"id":"2503.10307","title":"6D Object Pose Tracking in Internet Videos for Robotic Manipulation","created":"2025-03-13","cited_by_count":10,"area":null},{"id":"2506.07155","title":"GoTrack: Generic 6DoF Object Pose Refinement and Tracking","created":"2025-06-08","cited_by_count":10,"area":null},{"id":"2412.01052","title":"CRISP: Object Pose and Shape Estimation with Test-Time Adaptation","created":"2024-12-02","cited_by_count":9,"area":null},{"id":"2506.07996","title":"UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2508.02146","title":"ScrewSplat: An End-to-End Method for Articulated Object Recognition","created":"2025-08-04","cited_by_count":9,"area":null},{"id":"2509.18676","title":"3D Flow Diffusion Policy: Visuomotor Policy Learning via Generating Flow in 3D Space","created":"2025-09-23","cited_by_count":9,"area":"diffusion"},{"id":"2404.11401","title":"RainyScape: Unsupervised Rainy Scene Reconstruction using Decoupled Neural Rendering","created":"2024-04-17","cited_by_count":8,"area":null},{"id":"2410.20927","title":"VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions","created":"2024-10-28","cited_by_count":8,"area":"mllm"},{"id":"2501.05439","title":"From Simple to Complex Skills: The Case of In-Hand Object Reorientation","created":"2025-01-09","cited_by_count":8,"area":null},{"id":"2604.05621","title":"FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videos","created":"2026-04-07","cited_by_count":8,"area":null},{"id":"2308.06962","title":"Color-NeuS: Reconstructing Neural Implicit Surfaces with Color","created":"2023-08-14","cited_by_count":7,"area":null},{"id":"2504.13159","title":"Digital Twin Generation from Visual Data: A Survey","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2601.01050","title":"EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos","created":"2026-01-03","cited_by_count":7,"area":"diffusion"},{"id":"2602.06226","title":"ForeHOI: Feed-forward 3D Object Reconstruction from Daily Hand-Object Interaction Videos","created":"2026-02-05","cited_by_count":7,"area":null},{"id":"2403.07547","title":"SMURF: Continuous Dynamics for Motion-Deblurring Radiance Fields","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2504.13419","title":"Mono3R: Exploiting Monocular Cues for Geometric 3D Reconstruction","created":"2025-04-18","cited_by_count":6,"area":null},{"id":"2505.11282","title":"MTevent: A Multi-Task Event Camera Dataset for 6D Pose Estimation and Moving Object Detection","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2506.17119","title":"RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2310.17880","title":"Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representations","created":"2023-10-27","cited_by_count":5,"area":null},{"id":"2406.03625","title":"Degrees of Freedom Matter: Inferring Dynamics from Point Trajectories","created":"2024-06-05","cited_by_count":5,"area":null},{"id":"2407.08199","title":"SRPose: Two-view Relative Pose Estimation with Sparse Keypoints","created":"2024-07-11","cited_by_count":5,"area":null},{"id":"2410.05514","title":"Toward General Object-level Mapping from Sparse Views with 3D Diffusion Priors","created":"2024-10-07","cited_by_count":5,"area":"diffusion"},{"id":"2502.08643","title":"A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewards","created":"2025-02-12","cited_by_count":5,"area":null},{"id":"2502.17434","title":"V-HOP: Visuo-Haptic 6D Object Pose Tracking","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2504.20359","title":"PRISM-DP: Spatial Pose-based Observations for Diffusion-Policies via Segmentation, Mesh Generation, and Pose Tracking","created":"2025-04-29","cited_by_count":5,"area":"diffusion"},{"id":"2512.22581","title":"KV-Tracker: Real-Time Pose Tracking with Transformers","created":"2025-12-27","cited_by_count":5,"area":null},{"id":"2601.04194","title":"Choreographing a World of Dynamic Objects","created":"2026-01-07","cited_by_count":5,"area":null},{"id":"2606.18558","title":"MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction","created":"2026-06-17","cited_by_count":5,"area":null},{"id":"2312.16425","title":"In-Hand 3D Object Reconstruction from a Monocular RGB Video","created":"2023-12-27","cited_by_count":4,"area":null},{"id":"2402.02800","title":"Extreme Two-View Geometry From Object Poses with Diffusion Models","created":"2024-02-05","cited_by_count":4,"area":"diffusion"},{"id":"2502.10606","title":"HIPPo: Harnessing Image-to-3D Priors for Model-free Zero-shot 6D Pose Estimation","created":"2025-02-14","cited_by_count":4,"area":"diffusion"},{"id":"2602.08058","title":"Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling","created":"2026-02-08","cited_by_count":4,"area":null},{"id":"2401.04377","title":"Towards Real-World Aerial Vision Guidance with Categorical 6D Pose Tracker","created":"2024-01-09","cited_by_count":3,"area":null},{"id":"2404.16483","title":"Leveraging Pretrained Latent Representations for Few-Shot Imitation Learning on a Dexterous Robotic Hand","created":"2024-04-25","cited_by_count":3,"area":"offlinerl"},{"id":"2409.01814","title":"Segmenting Object Affordances: Reproducibility and Sensitivity to Scale","created":"2024-09-03","cited_by_count":3,"area":null},{"id":"2504.13179","title":"ViTa-Zero: Zero-shot Visuotactile Object 6D Pose Estimation","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2603.22102","title":"FreeArtGS: Articulated Gaussian Splatting Under Free-moving Scenario","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2607.06555","title":"ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation","created":"2026-07-07","cited_by_count":3,"area":null},{"id":"2404.03462","title":"You Only Scan Once: A Dynamic Scene Reconstruction Pipeline for 6-DoF Robotic Grasping of Novel Objects","created":"2024-04-04","cited_by_count":2,"area":null},{"id":"2407.12207","title":"NeuSurfEmb: A Complete Pipeline for Dense Correspondence-based 6D Object Pose Estimation without CAD Models","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2410.09467","title":"Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors","created":"2024-10-12","cited_by_count":2,"area":"diffusion"},{"id":"2506.08619","title":"A Probability-guided Sampler for Neural Implicit Surface Rendering","created":"2025-06-10","cited_by_count":2,"area":null},{"id":"2508.00354","title":"Omni-Scan: Creating Visually-Accurate Digital Twin Object Models Using a Bimanual Robot with Handover and Gaussian Splat Merging","created":"2025-08-01","cited_by_count":2,"area":null},{"id":"2508.15972","title":"UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation","created":"2025-08-21","cited_by_count":2,"area":"diffusion"},{"id":"2510.11687","title":"Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2510.20605","title":"OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2602.05555","title":"IndustryShapes: An RGB-D Benchmark dataset for 6D object pose estimation of industrial assembly components and tools","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2603.28045","title":"Event6D: Event-based Novel Object 6D Pose Tracking","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2606.08057","title":"EgoAERO: Learning Dexterous Manipulation from a Single Egocentric Video without Object Assets","created":"2026-06-06","cited_by_count":2,"area":null},{"id":"2609.05416","title":"WorldSculpt: Generating Compositional Worlds from Grounded Videos","created":"2026-09-04","cited_by_count":2,"area":null},{"id":"2307.15671","title":"TrackAgent: 6D Object Tracking via Reinforcement Learning","created":"2023-07-28","cited_by_count":1,"area":null},{"id":"2308.08856","title":"MV-ROPE: Multi-view Constraints for Robust Category-level Object Pose and Size Estimation","created":"2023-08-17","cited_by_count":1,"area":null},{"id":"2309.13570","title":"Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset","created":"2023-09-24","cited_by_count":1,"area":null},{"id":"2312.16218","title":"Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworks","created":"2023-12-24","cited_by_count":1,"area":"diffusion"},{"id":"2401.08937","title":"ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2402.11287","title":"Dense Matchers for Dense Tracking","created":"2024-02-17","cited_by_count":1,"area":null},{"id":"2406.10543","title":"NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows","created":"2024-06-15","cited_by_count":1,"area":null},{"id":"2409.02598","title":"SurgTrack: CAD-Free 3D Tracking of Real-world Surgical Instruments","created":"2024-09-04","cited_by_count":1,"area":null},{"id":"2410.13465","title":"Object Pose Estimation Using Implicit Representation For Transparent Objects","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2411.15860","title":"Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching","created":"2024-11-24","cited_by_count":1,"area":null},{"id":"2501.03525","title":"TexHOI: Reconstructing Textures of 3D Unknown Objects in Monocular Hand-Object Interaction Scenes","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2502.08646","title":"Poly-Autoregressive Prediction for Modeling Interactions","created":"2025-02-12","cited_by_count":1,"area":null},{"id":"2503.22437","title":"EndoLRMGS: Complete Endoscopic Scene Reconstruction combining Large Reconstruction Modelling and Gaussian Splatting","created":"2025-03-28","cited_by_count":1,"area":null}],"next_cursor":"100"}