{"total":201,"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":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315,"area":"lr"},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247,"area":null},{"id":"2303.14158","title":"BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects","created":"2023-03-24","cited_by_count":148,"area":null},{"id":"2311.15707","title":"SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation","created":"2023-11-27","cited_by_count":117,"area":null},{"id":"2311.14155","title":"GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence","created":"2023-11-23","cited_by_count":114,"area":null},{"id":"2311.18809","title":"FoundPose: Unseen Object Pose Estimation with Foundation Features","created":"2023-11-30","cited_by_count":109,"area":null},{"id":"2307.11067","title":"CNOS: A Strong Baseline for CAD-based Novel Object Segmentation","created":"2023-07-20","cited_by_count":87,"area":null},{"id":"2406.16862","title":"Dreamitate: Real-World Visuomotor Policy Learning via Video Generation","created":"2024-06-24","cited_by_count":87,"area":null},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84,"area":"mllm"},{"id":"2412.07759","title":"3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation","created":"2024-12-10","cited_by_count":71,"area":null},{"id":"2305.16309","title":"Imitating Task and Motion Planning with Visuomotor Transformers","created":"2023-05-25","cited_by_count":66,"area":"offlinerl"},{"id":"2403.09799","title":"BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objects","created":"2024-03-14","cited_by_count":60,"area":null},{"id":"2312.00947","title":"FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation models","created":"2023-12-01","cited_by_count":57,"area":null},{"id":"2405.01534","title":"Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks","created":"2024-05-02","cited_by_count":52,"area":null},{"id":"2605.12090","title":"World Action Models: The Next Frontier in Embodied AI","created":"2026-05-12","cited_by_count":50,"area":"wm"},{"id":"2503.18673","title":"Any6D: Model-free 6D Pose Estimation of Novel Objects","created":"2025-03-24","cited_by_count":49,"area":null},{"id":"2502.13143","title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation","created":"2025-02-18","cited_by_count":46,"area":"lr"},{"id":"2309.11986","title":"ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers","created":"2023-09-21","cited_by_count":45,"area":null},{"id":"2405.07801","title":"Deep Learning-Based Object Pose Estimation: A Comprehensive Survey","created":"2024-05-13","cited_by_count":40,"area":null},{"id":"2303.13612","title":"NOPE: Novel Object Pose Estimation from a Single Image","created":"2023-03-23","cited_by_count":38,"area":null},{"id":"2507.00990","title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","created":"2025-07-01","cited_by_count":38,"area":null},{"id":"2403.11510","title":"GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects","created":"2024-03-18","cited_by_count":33,"area":null},{"id":"2303.16730","title":"TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation","created":"2023-03-29","cited_by_count":32,"area":null},{"id":"2307.04751","title":"Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement","created":"2023-07-10","cited_by_count":29,"area":null},{"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":"2403.01517","title":"MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images","created":"2024-03-03","cited_by_count":28,"area":null},{"id":"2507.01099","title":"Geometry-aware 4D Video Generation for Robot Manipulation","created":"2025-07-01","cited_by_count":24,"area":"wm"},{"id":"2307.12172","title":"Challenges for Monocular 6D Object Pose Estimation in Robotics","created":"2023-07-22","cited_by_count":21,"area":null},{"id":"2404.10438","title":"The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement","created":"2024-04-16","cited_by_count":21,"area":null},{"id":"2305.17934","title":"ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenes","created":"2023-05-29","cited_by_count":20,"area":null},{"id":"2402.10778","title":"AutoGPT+P: Affordance-based Task Planning with Large Language Models","created":"2024-02-16","cited_by_count":19,"area":"lr"},{"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":"2604.19092","title":"RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation","created":"2026-04-21","cited_by_count":19,"area":"wm"},{"id":"2502.04293","title":"GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimation","created":"2025-02-06","cited_by_count":18,"area":null},{"id":"2505.04109","title":"One2Any: One-Reference 6D Pose Estimation for Any Object","created":"2025-05-07","cited_by_count":18,"area":null},{"id":"2305.01191","title":"EasyHeC: Accurate and Automatic Hand-eye Calibration via Differentiable Rendering and Space Exploration","created":"2023-05-02","cited_by_count":17,"area":null},{"id":"2311.12588","title":"HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation","created":"2023-11-21","cited_by_count":17,"area":null},{"id":"2512.10957","title":"SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model","created":"2025-12-11","cited_by_count":17,"area":null},{"id":"2403.10683","title":"GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splatting","created":"2024-03-15","cited_by_count":15,"area":null},{"id":"2411.19458","title":"Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning","created":"2024-11-29","cited_by_count":14,"area":null},{"id":"2503.17731","title":"Co-op: Correspondence-based Novel Object Pose Estimation","created":"2025-03-22","cited_by_count":14,"area":null},{"id":"2312.09031","title":"iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matching","created":"2023-12-14","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":"2403.18791","title":"Object Pose Estimation via the Aggregation of Diffusion Features","created":"2024-03-27","cited_by_count":12,"area":"diffusion"},{"id":"2411.11409","title":"IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2411.16106","title":"UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image","created":"2024-11-25","cited_by_count":12,"area":null},{"id":"2606.20781","title":"World Action Models: A Survey","created":"2026-06-18","cited_by_count":12,"area":"wm"},{"id":"2310.00463","title":"Diff-DOPE: Differentiable Deep Object Pose Estimation","created":"2023-09-30","cited_by_count":11,"area":null},{"id":"2403.08019","title":"MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation","created":"2024-03-12","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":"2406.16384","title":"High-resolution open-vocabulary object 6D pose estimation","created":"2024-06-24","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":"2510.08475","title":"DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos","created":"2025-10-09","cited_by_count":10,"area":null},{"id":"2306.00129","title":"Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objects","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2403.14628","title":"Zero-Shot Multi-Object Scene Completion","created":"2024-03-21","cited_by_count":9,"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":"2412.03570","title":"Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis","created":"2024-12-04","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":"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":"2504.06866","title":"GraspClutter6D: A Large-scale Real-world Dataset for Robust Perception and Grasping in Cluttered Scenes","created":"2025-04-09","cited_by_count":8,"area":null},{"id":"2303.16102","title":"KeyMatchNet: Zero-Shot Pose Estimation in 3D Point Clouds by Generalized Keypoint Matching","created":"2023-03-28","cited_by_count":7,"area":null},{"id":"2411.18011","title":"Manual-PA: Learning 3D Part Assembly from Instruction Diagrams","created":"2024-11-27","cited_by_count":7,"area":null},{"id":"2410.08152","title":"RayEmb: Arbitrary Landmark Detection in X-Ray Images Using Ray Embedding Subspace","created":"2024-10-10","cited_by_count":6,"area":null},{"id":"2504.02617","title":"PicoPose: Progressive Pixel-to-Pixel Correspondence Learning for Novel Object Pose Estimation","created":"2025-04-03","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":"2302.03744","title":"3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimation","created":"2023-02-07","cited_by_count":5,"area":null},{"id":"2404.03962","title":"RaSim: A Range-aware High-fidelity RGB-D Data Simulation Pipeline for Real-world Applications","created":"2024-04-05","cited_by_count":5,"area":null},{"id":"2407.04384","title":"Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos","created":"2024-07-05","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":"2508.11950","title":"DynamicPose: Real-time and Robust 6D Object Pose Tracking for Fast-Moving Cameras and Objects","created":"2025-08-16","cited_by_count":5,"area":null},{"id":"2512.22581","title":"KV-Tracker: Real-Time Pose Tracking with Transformers","created":"2025-12-27","cited_by_count":5,"area":null},{"id":"2604.27621","title":"Robot Learning from Human Videos: A Survey","created":"2026-04-30","cited_by_count":5,"area":null},{"id":"2311.09500","title":"Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimation","created":"2023-11-16","cited_by_count":4,"area":null},{"id":"2411.16668","title":"Diffusion Features for Zero-Shot 6DoF Object Pose Estimation","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2502.01800","title":"Flow-based Domain Randomization for Learning and Sequencing Robotic Skills","created":"2025-02-03","cited_by_count":4,"area":"deeprl"},{"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":"2503.15106","title":"Distilling 3D distinctive local descriptors for 6D pose estimation","created":"2025-03-19","cited_by_count":4,"area":null},{"id":"2508.04122","title":"Conditional Latent Diffusion Models for Zero-Shot Instance Segmentation","created":"2025-08-06","cited_by_count":4,"area":"diffusion"},{"id":"2510.18521","title":"RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2602.08058","title":"Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling","created":"2026-02-08","cited_by_count":4,"area":null},{"id":"2404.00891","title":"Marrying NeRF with Feature Matching for One-step Pose Estimation","created":"2024-04-01","cited_by_count":3,"area":null},{"id":"2404.06277","title":"Learning Embeddings with Centroid Triplet Loss for Object Identification in Robotic Grasping","created":"2024-04-09","cited_by_count":3,"area":null},{"id":"2408.08234","title":"Comparative Evaluation of 3D Reconstruction Methods for Object Pose Estimation","created":"2024-08-15","cited_by_count":3,"area":null},{"id":"2408.17297","title":"BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguities","created":"2024-08-30","cited_by_count":3,"area":null},{"id":"2410.21153","title":"Synthetica: Large Scale Synthetic Data for Robot Perception","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2411.03807","title":"GS2Pose: Two-stage 6D Object Pose Estimation Guided by Gaussian Splatting","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2503.03726","title":"Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Frames","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2503.23587","title":"PhysPose: Refining 6D Object Poses with Physical Constraints","created":"2025-03-30","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":"2505.02501","title":"Corr2Distrib: Making Ambiguous Correspondences an Ally to Predict Reliable 6D Pose Distributions","created":"2025-05-05","cited_by_count":3,"area":null},{"id":"2507.05751","title":"SenseShift6D: Multimodal RGB-D Benchmarking for Robust 6D Pose Estimation across Environment and Sensor Variations","created":"2025-07-08","cited_by_count":3,"area":null},{"id":"2509.16132","title":"Recovering Parametric Scenes from Very Few Time-of-Flight Pixels","created":"2025-09-19","cited_by_count":3,"area":null},{"id":"2510.10177","title":"HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation","created":"2025-10-11","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}],"next_cursor":"100"}