{"list":"other","total":66,"rows":[{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"2404.07191","title":"InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models","created":"2024-04-10","cited_by_count":433},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"1904.05767","title":"Learning joint reconstruction of hands and manipulated objects","created":"2019-04-11","cited_by_count":378},{"id":"2104.04631","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","created":"2021-04-09","cited_by_count":325},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"2007.09545","title":"ContactPose: A Dataset of Grasps with Object Contact and Hand Pose","created":"2020-07-19","cited_by_count":183},{"id":"2202.08227","title":"Ditto: Building Digital Twins of Articulated Objects from Interaction","created":"2022-02-16","cited_by_count":156},{"id":"2012.09856","title":"Reconstructing Hand-Object Interactions in the Wild","created":"2020-12-17","cited_by_count":144},{"id":"2104.07267","title":"ContactOpt: Optimizing Contact to Improve Grasps","created":"2021-04-15","cited_by_count":139},{"id":"2211.05272","title":"GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts","created":"2022-11-10","cited_by_count":139},{"id":"2203.15709","title":"OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction","created":"2022-03-29","cited_by_count":131},{"id":"2410.11831","title":"CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos","created":"2024-10-15","cited_by_count":128},{"id":"2506.16504","title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","created":"2025-06-19","cited_by_count":125},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124},{"id":"2308.07391","title":"PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects","created":"2023-08-14","cited_by_count":118},{"id":"2311.14155","title":"GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence","created":"2023-11-23","cited_by_count":114},{"id":"2410.13882","title":"Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model","created":"2024-10-03","cited_by_count":96},{"id":"2504.11451","title":"PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond","created":"2025-04-15","cited_by_count":95},{"id":"2004.08154","title":"Detailed 2D-3D Joint Representation for Human-Object Interaction","created":"2020-04-17","cited_by_count":93},{"id":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87},{"id":"2202.08432","title":"AKB-48: A Real-World Articulated Object Knowledge Base","created":"2022-02-17","cited_by_count":82},{"id":"2311.18448","title":"HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video","created":"2023-11-30","cited_by_count":78},{"id":"2501.10018","title":"DiffuEraser: A Diffusion Model for Video Inpainting","created":"2025-01-17","cited_by_count":72},{"id":"2504.14717","title":"TAPIP3D: Tracking Any Point in Persistent 3D Geometry","created":"2025-04-20","cited_by_count":69},{"id":"2502.19459","title":"ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting","created":"2025-02-26","cited_by_count":67},{"id":"2601.12993","title":"Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization","created":"2026-01-19","cited_by_count":66},{"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},{"id":"2207.12909","title":"AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction","created":"2022-07-26","cited_by_count":59},{"id":"2409.18121","title":"Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction","created":"2024-09-26","cited_by_count":54},{"id":"2304.12467","title":"Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstruction","created":"2023-04-24","cited_by_count":51},{"id":"2304.11970","title":"gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction","created":"2023-04-24","cited_by_count":50},{"id":"2503.18673","title":"Any6D: Model-free 6D Pose Estimation of Novel Objects","created":"2025-03-24","cited_by_count":49},{"id":"2404.11151","title":"REACTO: Reconstructing Articulated Objects from a Single Video","created":"2024-04-17","cited_by_count":45},{"id":"2006.15561","title":"Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion","created":"2020-06-28","cited_by_count":39},{"id":"2411.14280","title":"EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild","created":"2024-11-21","cited_by_count":36},{"id":"2211.16835","title":"Reconstructing Hand-Held Objects from Monocular Video","created":"2022-11-30","cited_by_count":35},{"id":"2306.00979","title":"Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Clouds","created":"2023-06-01","cited_by_count":34},{"id":"2501.14208","title":"You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations","created":"2025-01-24","cited_by_count":21},{"id":"2506.08334","title":"iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos","created":"2025-06-10","cited_by_count":19},{"id":"2509.01708","title":"Articulated Object Estimation in the Wild","created":"2025-09-01","cited_by_count":19},{"id":"2508.05506","title":"MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips","created":"2025-08-07","cited_by_count":17},{"id":"2509.17647","title":"VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Video","created":"2025-09-22","cited_by_count":15},{"id":"2105.08016","title":"StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects","created":"2021-05-17","cited_by_count":14},{"id":"2403.14937","title":"Survey on Modeling of Human-made Articulated Objects","created":"2024-03-22","cited_by_count":14},{"id":"2206.08497","title":"Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collections","created":"2022-06-17","cited_by_count":13},{"id":"2503.15898","title":"Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions","created":"2025-03-20","cited_by_count":13},{"id":"2507.02600","title":"ArtGS:3D Gaussian Splatting for Interactive Visual-Physical Modeling and Manipulation of Articulated Objects","created":"2025-07-03","cited_by_count":11},{"id":"2510.21447","title":"PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis","created":"2025-10-24","cited_by_count":10},{"id":"2407.20566","title":"Monocular Human-Object Reconstruction in the Wild","created":"2024-07-30","cited_by_count":9},{"id":"2504.17441","title":"Predict-Optimize-Distill: A Self-Improving Cycle for 4D Object Understanding","created":"2025-04-24","cited_by_count":8},{"id":"2508.18213","title":"Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance","created":"2025-08-25","cited_by_count":8},{"id":"2508.16465","title":"HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images","created":"2025-08-22","cited_by_count":3},{"id":"2404.14968","title":"CenterArt: Joint Shape Reconstruction and 6-DoF Grasp Estimation of Articulated Objects","created":"2024-04-23","cited_by_count":1}],"next_cursor":null}