{"list":"other","total":51,"rows":[{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"1801.07791","title":"PointCNN: Convolution On $\\mathcal{X}$-Transformed Points","created":"2018-01-23","cited_by_count":764},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2312.10035","title":"Point Transformer V3: Simpler, Faster, Stronger","created":"2023-12-15","cited_by_count":589},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"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":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"2009.09633","title":"3D-FUTURE: 3D Furniture shape with TextURE","created":"2020-09-21","cited_by_count":311},{"id":"2012.02206","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","created":"2020-12-03","cited_by_count":218},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204},{"id":"1908.06109","title":"RIO: 3D Object Instance Re-Localization in Changing Indoor Environments","created":"2019-08-16","cited_by_count":188},{"id":"2101.02692","title":"Where2Act: From Pixels to Actions for Articulated 3D Objects","created":"2021-01-07","cited_by_count":182},{"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":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175},{"id":"2309.05251","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","created":"2023-09-11","cited_by_count":146},{"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":"2212.01558","title":"PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models","created":"2022-12-03","cited_by_count":118},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115},{"id":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","cited_by_count":110},{"id":"2411.07184","title":"SAMPart3D: Segment Any Part in 3D Objects","created":"2024-11-11","cited_by_count":97},{"id":"2301.02508","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","created":"2023-01-06","cited_by_count":78},{"id":"2212.00836","title":"UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding","created":"2022-12-01","cited_by_count":69},{"id":"2405.17596","title":"GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane","created":"2024-05-27","cited_by_count":53},{"id":"2406.17741","title":"Point-SAM: Promptable 3D Segmentation Model for Point Clouds","created":"2024-06-25","cited_by_count":50},{"id":"2407.01525","title":"ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities","created":"2024-07-01","cited_by_count":47},{"id":"2510.23607","title":"Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations","created":"2025-10-27","cited_by_count":45},{"id":"2509.06784","title":"P3-SAM: Native 3D Part Segmentation","created":"2025-09-08","cited_by_count":43},{"id":"2504.05786","title":"How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM","created":"2025-04-08","cited_by_count":42},{"id":"2308.16632","title":"3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation","created":"2023-08-31","cited_by_count":36},{"id":"2407.13761","title":"SegPoint: Segment Any Point Cloud via Large Language Model","created":"2024-07-18","cited_by_count":35},{"id":"2405.21066","title":"Mixed Diffusion for 3D Indoor Scene Synthesis","created":"2024-05-31","cited_by_count":32},{"id":"2411.13550","title":"Find Any Part in 3D","created":"2024-11-20","cited_by_count":32},{"id":"2412.18450","title":"3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding","created":"2024-12-24","cited_by_count":27},{"id":"2501.18672","title":"Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting","created":"2025-01-30","cited_by_count":22},{"id":"2310.18511","title":"3DCoMPaT$^{++}$: An improved Large-scale 3D Vision Dataset for Compositional Recognition","created":"2023-10-27","cited_by_count":21},{"id":"2603.03283","title":"Utonia: Toward One Encoder for All Point Clouds","created":"2026-03-03","cited_by_count":21},{"id":"2504.13153","title":"Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs","created":"2025-04-17","cited_by_count":10},{"id":"2511.01294","title":"Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects","created":"2025-11-03","cited_by_count":9}],"next_cursor":null}