{"list":"other","total":76,"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":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"2309.16653","title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","created":"2023-09-28","cited_by_count":843},{"id":"2309.13101","title":"Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction","created":"2023-09-22","cited_by_count":759},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2301.10241","title":"K-Planes: Explicit Radiance Fields in Space, Time, and Appearance","created":"2023-01-24","cited_by_count":746},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2302.04264","title":"Nerfstudio: A Modular Framework for Neural Radiance Field Development","created":"2023-02-08","cited_by_count":600},{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"2012.12247","title":"Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video","created":"2020-12-22","cited_by_count":471},{"id":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420},{"id":"2103.15875","title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","created":"2021-03-29","cited_by_count":415},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"2011.12950","title":"Space-time Neural Irradiance Fields for Free-Viewpoint Video","created":"2020-11-25","cited_by_count":414},{"id":"2205.15585","title":"Decomposing NeRF for Editing via Feature Field Distillation","created":"2022-05-31","cited_by_count":371},{"id":"2210.05714","title":"Visual Language Maps for Robot Navigation","created":"2022-10-11","cited_by_count":365},{"id":"2205.15285","title":"Fast Dynamic Radiance Fields with Time-Aware Neural Voxels","created":"2022-05-30","cited_by_count":346},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304},{"id":"2309.16585","title":"Text-to-3D using Gaussian Splatting","created":"2023-09-28","cited_by_count":299},{"id":"2311.07885","title":"One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion","created":"2023-11-14","cited_by_count":283},{"id":"2311.11700","title":"GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting","created":"2023-11-20","cited_by_count":278},{"id":"2012.09790","title":"Neural Radiance Flow for 4D View Synthesis and Video Processing","created":"2020-12-17","cited_by_count":270},{"id":"2211.11610","title":"Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering","created":"2022-11-21","cited_by_count":217},{"id":"2312.07843","title":"Foundation Models in Robotics: Applications, Challenges, and the Future","created":"2023-12-13","cited_by_count":216},{"id":"2311.18651","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","created":"2023-11-30","cited_by_count":210},{"id":"2311.18482","title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","created":"2023-11-30","cited_by_count":208},{"id":"2209.03494","title":"Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations","created":"2022-09-07","cited_by_count":196},{"id":"2206.08929","title":"TAVA: Template-free Animatable Volumetric Actors","created":"2022-06-17","cited_by_count":172},{"id":"2210.05663","title":"CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory","created":"2022-10-11","cited_by_count":165},{"id":"2209.09874","title":"Open-vocabulary Queryable Scene Representations for Real World Planning","created":"2022-09-20","cited_by_count":160},{"id":"2210.15947","title":"NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields","created":"2022-10-28","cited_by_count":152},{"id":"2403.09227","title":"BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation","created":"2024-03-14","cited_by_count":148},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133},{"id":"2212.00190","title":"Mixed Neural Voxels for Fast Multi-view Video Synthesis","created":"2022-12-01","cited_by_count":127},{"id":"2206.06481","title":"RigNeRF: Fully Controllable Neural 3D Portraits","created":"2022-06-13","cited_by_count":126},{"id":"2312.00112","title":"DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting","created":"2023-11-30","cited_by_count":124},{"id":"2401.09419","title":"GARField: Group Anything with Radiance Fields","created":"2024-01-17","cited_by_count":109},{"id":"2101.01602","title":"STaR: Self-supervised Tracking and Reconstruction of Rigid Objects in Motion with Neural Rendering","created":"2020-12-22","cited_by_count":76},{"id":"2404.10179","title":"Scaling Instructable Agents Across Many Simulated Worlds","created":"2024-03-13","cited_by_count":71},{"id":"2303.16894","title":"ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance","created":"2023-03-29","cited_by_count":70},{"id":"2311.10091","title":"Adaptive Shells for Efficient Neural Radiance Field Rendering","created":"2023-11-16","cited_by_count":69},{"id":"2112.01983","title":"CoNeRF: Controllable Neural Radiance Fields","created":"2021-12-03","cited_by_count":65},{"id":"2401.17807","title":"Advances in 3D Generation: A Survey","created":"2024-01-31","cited_by_count":63},{"id":"2212.13545","title":"Interactive Segmentation of Radiance Fields","created":"2022-12-27","cited_by_count":60},{"id":"2303.11327","title":"3D Concept Learning and Reasoning from Multi-View Images","created":"2023-03-20","cited_by_count":60},{"id":"2204.10850","title":"Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulation","created":"2022-04-22","cited_by_count":57},{"id":"2402.10483","title":"GaussianHair: Hair Modeling and Rendering with Light-aware Gaussians","created":"2024-02-16","cited_by_count":48},{"id":"2310.17527","title":"Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction","created":"2023-10-26","cited_by_count":43},{"id":"2310.03059","title":"Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models","created":"2023-10-04","cited_by_count":42},{"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":"2208.00949","title":"VolTeMorph: Realtime, Controllable and Generalisable Animation of Volumetric Representations","created":"2022-08-01","cited_by_count":36},{"id":"2403.11492","title":"SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction","created":"2024-03-18","cited_by_count":34},{"id":"2312.05664","title":"CoGS: Controllable Gaussian Splatting","created":"2023-12-09","cited_by_count":32},{"id":"2212.04247","title":"EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points","created":"2022-12-07","cited_by_count":30},{"id":"2403.15064","title":"Recent Trends in 3D Reconstruction of General Non-Rigid Scenes","created":"2024-03-22","cited_by_count":28},{"id":"2404.07989","title":"Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding","created":"2024-04-11","cited_by_count":23},{"id":"2311.11013","title":"Implicit Event-RGBD Neural SLAM","created":"2023-11-18","cited_by_count":16},{"id":"2209.08503","title":"Revisiting Rolling Shutter Bundle Adjustment: Toward Accurate and Fast Solution","created":"2022-09-18","cited_by_count":13},{"id":"2310.16383","title":"Open-NeRF: Towards Open Vocabulary NeRF Decomposition","created":"2023-10-25","cited_by_count":13},{"id":"2312.07378","title":"X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfer","created":"2023-12-12","cited_by_count":12},{"id":"2211.08610","title":"CoNFies: Controllable Neural Face Avatars","created":"2022-11-16","cited_by_count":4}],"next_cursor":null}