{"list":"other","total":65,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1904.08755","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","created":"2019-04-18","cited_by_count":1208},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"1711.10275","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","created":"2017-11-28","cited_by_count":748},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"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":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2406.02523","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","created":"2024-06-04","cited_by_count":407},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"1701.01370","title":"Learning from Synthetic Humans","created":"2017-01-05","cited_by_count":359},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303},{"id":"2301.04195","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","created":"2023-01-10","cited_by_count":295},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289},{"id":"1908.00222","title":"Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling","created":"2019-08-01","cited_by_count":286},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268},{"id":"1406.2031","title":"Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts","created":"2014-06-08","cited_by_count":232},{"id":"2203.01509","title":"SoftGroup for 3D Instance Segmentation on Point Clouds","created":"2022-03-03","cited_by_count":200},{"id":"1908.06109","title":"RIO: 3D Object Instance Re-Localization in Changing Indoor Environments","created":"2019-08-16","cited_by_count":188},{"id":"2211.16312","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","created":"2022-11-29","cited_by_count":177},{"id":"2312.08168","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","created":"2023-12-13","cited_by_count":175},{"id":"2306.11290","title":"Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation","created":"2023-06-20","cited_by_count":167},{"id":"2202.08227","title":"Ditto: Building Digital Twins of Articulated Objects from Interaction","created":"2022-02-16","cited_by_count":156},{"id":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147},{"id":"2403.03949","title":"Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation","created":"2024-03-06","cited_by_count":144},{"id":"2406.11824","title":"Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation","created":"2024-06-17","cited_by_count":137},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133},{"id":"2108.02350","title":"Hierarchical Aggregation for 3D Instance Segmentation","created":"2021-08-05","cited_by_count":127},{"id":"1903.03911","title":"Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes","created":"2019-03-10","cited_by_count":119},{"id":"2308.07391","title":"PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects","created":"2023-08-14","cited_by_count":118},{"id":"2405.11656","title":"URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images","created":"2024-05-19","cited_by_count":111},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110},{"id":"2202.08432","title":"AKB-48: A Real-World Articulated Object Knowledge Base","created":"2022-02-17","cited_by_count":82},{"id":"2403.09637","title":"GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping","created":"2024-03-14","cited_by_count":78},{"id":"2404.03575","title":"DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling","created":"2024-04-04","cited_by_count":72},{"id":"2203.16421","title":"OPD: Single-view 3D Openable Part Detection","created":"2022-03-30","cited_by_count":54},{"id":"2312.09570","title":"CAGE: Controllable Articulation GEneration","created":"2023-12-15","cited_by_count":52},{"id":"2409.02389","title":"Multi-modal Situated Reasoning in 3D Scenes","created":"2024-09-04","cited_by_count":51},{"id":"2404.11151","title":"REACTO: Reconstructing Articulated Objects from a Single Video","created":"2024-04-17","cited_by_count":45},{"id":"2407.20727","title":"SceneTeller: Language-to-3D Scene Generation","created":"2024-07-30","cited_by_count":43},{"id":"2303.14087","title":"OPDMulti: Openable Part Detection for Multiple Objects","created":"2023-03-24","cited_by_count":39},{"id":"2401.08577","title":"MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World","created":"2024-01-16","cited_by_count":39},{"id":"2012.00284","title":"Visual Identification of Articulated Object Parts","created":"2020-12-01","cited_by_count":37},{"id":"2203.16531","title":"Understanding 3D Object Articulation in Internet Videos","created":"2022-03-30","cited_by_count":36},{"id":"2404.00989","title":"360+x: A Panoptic Multi-modal Scene Understanding Dataset","created":"2024-04-01","cited_by_count":35},{"id":"2303.14541","title":"UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes","created":"2023-03-25","cited_by_count":31},{"id":"2304.14880","title":"SGAligner : 3D Scene Alignment with Scene Graphs","created":"2023-04-28","cited_by_count":30},{"id":"2404.00469","title":"SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs","created":"2024-03-30","cited_by_count":29},{"id":"1910.01210","title":"Embodied Language Grounding with 3D Visual Feature Representations","created":"2019-10-02","cited_by_count":20},{"id":"2010.11735","title":"Self-Supervised Learning of Part Mobility from Point Cloud Sequence","created":"2020-10-20","cited_by_count":18},{"id":"2407.05862","title":"Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning","created":"2024-07-08","cited_by_count":16},{"id":"2409.06703","title":"LEIA: Latent View-invariant Embeddings for Implicit 3D Articulation","created":"2024-09-10","cited_by_count":16},{"id":"2405.20008","title":"Sharing Key Semantics in Transformer Makes Efficient Image Restoration","created":"2024-05-30","cited_by_count":14},{"id":"2406.02461","title":"RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpainting","created":"2024-06-04","cited_by_count":14},{"id":"1612.07310","title":"Beyond Holistic Object Recognition: Enriching Image Understanding with Part States","created":"2016-12-15","cited_by_count":13},{"id":"2407.11564","title":"SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation","created":"2024-07-16","cited_by_count":12},{"id":"2308.00055","title":"Towards Building AI-CPS with NVIDIA Isaac Sim: An Industrial Benchmark and Case Study for Robotics Manipulation","created":"2023-07-31","cited_by_count":11},{"id":"2307.05263","title":"Pegasus Simulator: An Isaac Sim Framework for Multiple Aerial Vehicles Simulation","created":"2023-07-11","cited_by_count":10},{"id":"2309.14737","title":"Volumetric Semantically Consistent 3D Panoptic Mapping","created":"2023-09-26","cited_by_count":10},{"id":"2403.14121","title":"External Knowledge Enhanced 3D Scene Generation from Sketch","created":"2024-03-21","cited_by_count":9},{"id":"2310.16737","title":"Translating Universal Scene Descriptions into Knowledge Graphs for Robotic Environment","created":"2023-10-25","cited_by_count":7},{"id":"2302.03566","title":"Look Around and Learn: Self-Training Object Detection by Exploration","created":"2023-02-07","cited_by_count":2}],"next_cursor":null}