{"list":"other","total":87,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"1801.09847","title":"Open3D: A Modern Library for 3D Data Processing","created":"2018-01-30","cited_by_count":721},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2405.05941","title":"Evaluating Real-World Robot Manipulation Policies in Simulation","created":"2024-05-09","cited_by_count":495},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304},{"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":"2304.06790","title":"Inpaint Anything: Segment Anything Meets Image Inpainting","created":"2023-04-13","cited_by_count":233},{"id":"2305.08275","title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","created":"2023-05-14","cited_by_count":202},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200},{"id":"2211.11682","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","created":"2022-11-21","cited_by_count":187},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181},{"id":"2211.16312","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","created":"2022-11-29","cited_by_count":177},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177},{"id":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175},{"id":"2002.12212","title":"Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image","created":"2020-02-27","cited_by_count":172},{"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":"2303.14207","title":"DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis","created":"2023-03-24","cited_by_count":166},{"id":"2012.09793","title":"SceneFormer: Indoor Scene Generation with Transformers","created":"2020-12-17","cited_by_count":158},{"id":"1811.11187","title":"Scan2CAD: Learning CAD Model Alignment in RGB-D Scans","created":"2018-11-27","cited_by_count":142},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133},{"id":"2312.10671","title":"Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance","created":"2023-12-17","cited_by_count":124},{"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":"2402.04717","title":"InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior","created":"2024-02-07","cited_by_count":117},{"id":"2311.14155","title":"GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence","created":"2023-11-23","cited_by_count":114},{"id":"2401.03407","title":"Bilateral Reference for High-Resolution Dichotomous Image Segmentation","created":"2024-01-07","cited_by_count":112},{"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":"1811.12463","title":"Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models","created":"2018-11-29","cited_by_count":106},{"id":"2312.00093","title":"GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs","created":"2023-11-30","cited_by_count":97},{"id":"2410.07408","title":"Automated Creation of Digital Cousins for Robust Policy Learning","created":"2024-10-09","cited_by_count":91},{"id":"2303.04748","title":"CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP","created":"2023-03-08","cited_by_count":89},{"id":"2309.00616","title":"OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation","created":"2023-09-01","cited_by_count":82},{"id":"2312.06644","title":"AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes","created":"2023-12-11","cited_by_count":82},{"id":"2304.00788","title":"Open-Vocabulary Point-Cloud Object Detection without 3D Annotation","created":"2023-04-03","cited_by_count":81},{"id":"1608.05137","title":"IM2CAD","created":"2016-08-18","cited_by_count":78},{"id":"2301.09629","title":"LEGO-Net: Learning Regular Rearrangements of Objects in Rooms","created":"2023-01-23","cited_by_count":76},{"id":"2407.20229","title":"Improving 2D Feature Representations by 3D-Aware Fine-Tuning","created":"2024-07-29","cited_by_count":71},{"id":"2203.01929","title":"CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation","created":"2022-03-03","cited_by_count":70},{"id":"1808.02201","title":"Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image","created":"2018-08-07","cited_by_count":69},{"id":"2112.01988","title":"ROCA: Robust CAD Model Retrieval and Alignment from a Single Image","created":"2021-12-03","cited_by_count":67},{"id":"2007.13034","title":"Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve","created":"2020-07-26","cited_by_count":65},{"id":"2304.04909","title":"SATR: Zero-Shot Semantic Segmentation of 3D Shapes","created":"2023-04-11","cited_by_count":62},{"id":"2204.03635","title":"Zero-Shot Category-Level Object Pose Estimation","created":"2022-04-07","cited_by_count":57},{"id":"2311.18610","title":"DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Image","created":"2023-11-30","cited_by_count":48},{"id":"2403.09675","title":"Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases","created":"2024-02-05","cited_by_count":45},{"id":"2207.08656","title":"Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes","created":"2022-07-18","cited_by_count":44},{"id":"2108.09368","title":"Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image","created":"2021-08-20","cited_by_count":39},{"id":"2311.00457","title":"Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture","created":"2023-11-01","cited_by_count":37},{"id":"2410.15971","title":"Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly","created":"2024-10-21","cited_by_count":35},{"id":"2012.04641","title":"Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videos","created":"2020-12-08","cited_by_count":33},{"id":"2108.10743","title":"DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization","created":"2021-08-24","cited_by_count":33},{"id":"2404.07445","title":"Multi-view Aggregation Network for Dichotomous Image Segmentation","created":"2024-04-11","cited_by_count":28},{"id":"2001.02149","title":"General 3D Room Layout from a Single View by Render-and-Compare","created":"2020-01-07","cited_by_count":21},{"id":"2210.01044","title":"SPARC: Sparse Render-and-Compare for CAD model alignment in a single RGB image","created":"2022-10-03","cited_by_count":19},{"id":"2305.12497","title":"PanoContext-Former: Panoramic Total Scene Understanding with a Transformer","created":"2023-05-21","cited_by_count":19},{"id":"2410.23643","title":"SceneComplete: Open-World 3D Scene Completion in Cluttered Real World Environments for Robot Manipulation","created":"2024-10-31","cited_by_count":18},{"id":"2408.02211","title":"SceneMotifCoder: Example-driven Visual Program Learning for Generating 3D Object Arrangements","created":"2024-08-05","cited_by_count":17},{"id":"2410.24001","title":"ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D Images","created":"2024-10-31","cited_by_count":17},{"id":"2403.18922","title":"Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D","created":"2024-03-27","cited_by_count":15},{"id":"2306.09011","title":"CAD-Estate: Large-scale CAD Model Annotation in RGB Videos","created":"2023-06-15","cited_by_count":14},{"id":"2410.15536","title":"GRS: Generating Robotic Simulation Tasks from Real-World Images","created":"2024-10-20","cited_by_count":13},{"id":"2406.11579","title":"Duoduo CLIP: Efficient 3D Understanding with Multi-View Images","created":"2024-06-17","cited_by_count":12},{"id":"2306.06212","title":"Aladdin: Zero-Shot Hallucination of Stylized 3D Assets from Abstract Scene Descriptions","created":"2023-06-09","cited_by_count":11},{"id":"2401.00405","title":"Generalizing Single-View 3D Shape Retrieval to Occlusions and Unseen Objects","created":"2023-12-31","cited_by_count":8},{"id":"2104.07986","title":"Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image","created":"2021-04-16","cited_by_count":7},{"id":"2403.15161","title":"FastCAD: Real-Time CAD Retrieval and Alignment from Scans and Videos","created":"2024-03-22","cited_by_count":7},{"id":"2306.09077","title":"Estimating Generic 3D Room Structures from 2D Annotations","created":"2023-06-15","cited_by_count":6},{"id":"2312.12418","title":"LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset","created":"2023-12-19","cited_by_count":5},{"id":"2403.12301","title":"R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding","created":"2024-03-18","cited_by_count":4}],"next_cursor":null}