{"total":575,"rows":[{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559,"area":null},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363,"area":null},{"id":"2312.07920","title":"DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes","created":"2023-12-13","cited_by_count":360,"area":null},{"id":"2304.14365","title":"Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving","created":"2023-04-27","cited_by_count":332,"area":"wm"},{"id":"2308.01898","title":"UniSim: A Neural Closed-Loop Sensor Simulator","created":"2023-08-03","cited_by_count":297,"area":null},{"id":"2111.14643","title":"Urban Radiance Fields","created":"2021-11-29","cited_by_count":263,"area":null},{"id":"2205.04334","title":"Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation","created":"2022-05-09","cited_by_count":243,"area":null},{"id":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231,"area":null},{"id":"2111.14690","title":"DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion","created":"2021-11-29","cited_by_count":217,"area":null},{"id":"2111.01007","title":"Projected GANs Converge Faster","created":"2021-11-01","cited_by_count":208,"area":null},{"id":"2309.16553","title":"MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond","created":"2023-09-28","cited_by_count":185,"area":null},{"id":"2210.00379","title":"NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)","created":"2022-10-01","cited_by_count":158,"area":null},{"id":"2405.17429","title":"GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction","created":"2024-05-27","cited_by_count":157,"area":null},{"id":"2203.15224","title":"Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation","created":"2022-03-29","cited_by_count":152,"area":null},{"id":"2403.12722","title":"HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting","created":"2024-03-19","cited_by_count":142,"area":null},{"id":"2305.14093","title":"Weakly Supervised 3D Open-vocabulary Segmentation","created":"2023-05-23","cited_by_count":135,"area":null},{"id":"2206.09474","title":"3D Object Detection for Autonomous Driving: A Comprehensive Survey","created":"2022-06-19","cited_by_count":132,"area":null},{"id":"2304.05170","title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","created":"2023-04-11","cited_by_count":131,"area":null},{"id":"2209.05324","title":"Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe","created":"2022-09-12","cited_by_count":122,"area":null},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117,"area":null},{"id":"2306.10013","title":"PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation","created":"2023-06-16","cited_by_count":115,"area":null},{"id":"2405.03520","title":"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond","created":"2024-05-06","cited_by_count":111,"area":"wm"},{"id":"2406.01493","title":"Learning Temporally Consistent Video Depth from Video Diffusion Priors","created":"2024-06-03","cited_by_count":100,"area":"diffusion"},{"id":"2209.03954","title":"Learning to Generate Realistic LiDAR Point Clouds","created":"2022-09-08","cited_by_count":93,"area":"wm"},{"id":"2306.15670","title":"Symphonize 3D Semantic Scene Completion with Contextual Instance Queries","created":"2023-06-27","cited_by_count":90,"area":null},{"id":"2412.01718","title":"HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving","created":"2024-12-02","cited_by_count":90,"area":"wm"},{"id":"2412.04384","title":"GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction","created":"2024-12-05","cited_by_count":86,"area":null},{"id":"2311.01448","title":"UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation","created":"2023-11-02","cited_by_count":78,"area":null},{"id":"2306.09001","title":"SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving","created":"2023-06-15","cited_by_count":75,"area":null},{"id":"2407.05921","title":"TAPVid-3D: A Benchmark for Tracking Any Point in 3D","created":"2024-07-08","cited_by_count":72,"area":null},{"id":"2404.00815","title":"Towards Realistic Scene Generation with LiDAR Diffusion Models","created":"2024-03-31","cited_by_count":69,"area":"wm"},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67,"area":"wm"},{"id":"2202.02980","title":"3D Object Detection from Images for Autonomous Driving: A Survey","created":"2022-02-07","cited_by_count":66,"area":null},{"id":"2401.01454","title":"A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook","created":"2024-01-02","cited_by_count":66,"area":null},{"id":"2301.07668","title":"Behind the Scenes: Density Fields for Single View Reconstruction","created":"2023-01-18","cited_by_count":63,"area":null},{"id":"2404.08351","title":"OmniSat: Self-Supervised Modality Fusion for Earth Observation","created":"2024-04-12","cited_by_count":63,"area":null},{"id":"2503.16591","title":"UniK3D: Universal Camera Monocular 3D Estimation","created":"2025-03-20","cited_by_count":62,"area":null},{"id":"2309.09668","title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","created":"2023-09-18","cited_by_count":60,"area":null},{"id":"2501.11260","title":"A Survey of World Models for Autonomous Driving","created":"2025-01-20","cited_by_count":60,"area":"wm"},{"id":"2206.07704","title":"Waymo Open Dataset: Panoramic Video Panoptic Segmentation","created":"2022-06-15","cited_by_count":58,"area":null},{"id":"2303.12074","title":"CC3D: Layout-Conditioned Generation of Compositional 3D Scenes","created":"2023-03-21","cited_by_count":58,"area":null},{"id":"2306.08045","title":"Efficient 3D Semantic Segmentation with Superpoint Transformer","created":"2023-06-13","cited_by_count":57,"area":null},{"id":"2307.10776","title":"Urban Radiance Field Representation with Deformable Neural Mesh Primitives","created":"2023-07-20","cited_by_count":55,"area":null},{"id":"2309.09256","title":"LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models","created":"2023-09-17","cited_by_count":55,"area":"wm"},{"id":"2211.12145","title":"Uncertainty-aware Vision-based Metric Cross-view Geolocalization","created":"2022-11-22","cited_by_count":54,"area":null},{"id":"2404.02903","title":"LidarDM: Generative LiDAR Simulation in a Generated World","created":"2024-04-03","cited_by_count":54,"area":null},{"id":"2308.12967","title":"NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes","created":"2023-08-24","cited_by_count":53,"area":null},{"id":"2405.13675","title":"Context and Geometry Aware Voxel Transformer for Semantic Scene Completion","created":"2024-05-22","cited_by_count":50,"area":null},{"id":"2406.17741","title":"Point-SAM: Promptable 3D Segmentation Model for Point Clouds","created":"2024-06-25","cited_by_count":50,"area":null},{"id":"2208.10925","title":"Vox-Surf: Voxel-based Implicit Surface Representation","created":"2022-08-21","cited_by_count":49,"area":null},{"id":"2204.07548","title":"Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation","created":"2022-04-15","cited_by_count":47,"area":null},{"id":"2304.10406","title":"LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields","created":"2023-04-20","cited_by_count":47,"area":null},{"id":"2403.10094","title":"RangeLDM: Fast Realistic LiDAR Point Cloud Generation","created":"2024-03-15","cited_by_count":47,"area":"wm"},{"id":"2207.11860","title":"Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation","created":"2022-07-25","cited_by_count":46,"area":null},{"id":"2303.03361","title":"Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision","created":"2023-03-06","cited_by_count":44,"area":null},{"id":"2311.17707","title":"SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation","created":"2023-11-29","cited_by_count":44,"area":null},{"id":"2403.08766","title":"MonoOcc: Digging into Monocular Semantic Occupancy Prediction","created":"2024-03-13","cited_by_count":44,"area":null},{"id":"2406.06526","title":"Generative Gaussian Splatting for Unbounded 3D City Generation","created":"2024-06-10","cited_by_count":44,"area":null},{"id":"2601.05083","title":"Driving on Registers","created":"2026-01-08","cited_by_count":44,"area":"driving"},{"id":"2312.02158","title":"PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness","created":"2023-12-04","cited_by_count":42,"area":null},{"id":"2403.13470","title":"Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion","created":"2024-03-20","cited_by_count":40,"area":"wm"},{"id":"2501.02464","title":"Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera","created":"2025-01-05","cited_by_count":40,"area":null},{"id":"2202.11542","title":"Amodal Panoptic Segmentation","created":"2022-02-23","cited_by_count":38,"area":null},{"id":"2210.06778","title":"X-Align: Cross-Modal Cross-View Alignment for Bird's-Eye-View Segmentation","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2308.16714","title":"Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perception","created":"2023-08-31","cited_by_count":38,"area":null},{"id":"2211.13226","title":"ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field","created":"2022-11-23","cited_by_count":37,"area":null},{"id":"2311.05607","title":"Real-Time Neural Rasterization for Large Scenes","created":"2023-11-09","cited_by_count":37,"area":null},{"id":"2405.05173","title":"A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective","created":"2024-05-08","cited_by_count":37,"area":null},{"id":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","cited_by_count":37,"area":null},{"id":"2403.20079","title":"SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior","created":"2024-03-29","cited_by_count":36,"area":"wm"},{"id":"2302.04233","title":"SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Images","created":"2023-02-08","cited_by_count":35,"area":null},{"id":"2312.08372","title":"SAM-guided Graph Cut for 3D Instance Segmentation","created":"2023-12-13","cited_by_count":35,"area":null},{"id":"2404.00989","title":"360+x: A Panoptic Multi-modal Scene Understanding Dataset","created":"2024-04-01","cited_by_count":35,"area":null},{"id":"2205.13281","title":"Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challenges","created":"2022-05-26","cited_by_count":34,"area":null},{"id":"2412.21117","title":"Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation","created":"2024-12-30","cited_by_count":34,"area":"diffusion"},{"id":"2306.00977","title":"AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation","created":"2023-06-01","cited_by_count":33,"area":null},{"id":"2311.11762","title":"MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representations","created":"2023-11-20","cited_by_count":33,"area":"wm"},{"id":"2401.06003","title":"TRIPS: Trilinear Point Splatting for Real-Time Radiance Field Rendering","created":"2024-01-11","cited_by_count":33,"area":null},{"id":"2603.24581","title":"Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving","created":"2026-03-25","cited_by_count":33,"area":"wm"},{"id":"2203.05056","title":"SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Driving","created":"2022-03-09","cited_by_count":32,"area":null},{"id":"2211.00385","title":"Behavioral Intention Prediction in Driving Scenes: A Survey","created":"2022-11-01","cited_by_count":30,"area":null},{"id":"2309.16179","title":"BEVHeight++: Toward Robust Visual Centric 3D Object Detection","created":"2023-09-28","cited_by_count":30,"area":null},{"id":"2412.01745","title":"Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes","created":"2024-12-02","cited_by_count":30,"area":null},{"id":"2310.15975","title":"Data-driven Traffic Simulation: A Comprehensive Review","created":"2023-10-24","cited_by_count":29,"area":null},{"id":"2410.17932","title":"VR-Splatting: Foveated Radiance Field Rendering via 3D Gaussian Splatting and Neural Points","created":"2024-10-23","cited_by_count":29,"area":null},{"id":"2309.13549","title":"Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset","created":"2023-09-24","cited_by_count":28,"area":null},{"id":"2310.07522","title":"S4C: Self-Supervised Semantic Scene Completion with Neural Fields","created":"2023-10-11","cited_by_count":28,"area":null},{"id":"2309.14563","title":"Towards a statistical theory of data selection under weak supervision","created":"2023-09-25","cited_by_count":27,"area":null},{"id":"2404.02742","title":"LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesis","created":"2024-04-03","cited_by_count":27,"area":null},{"id":"2407.19628","title":"Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformer","created":"2024-07-29","cited_by_count":27,"area":"wm"},{"id":"2507.14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2507.22412","title":"UAVScenes: A Multi-Modal Dataset for UAVs","created":"2025-07-30","cited_by_count":27,"area":null},{"id":"2202.13388","title":"PanoFlow: Learning 360{\\deg} Optical Flow for Surrounding Temporal Understanding","created":"2022-02-27","cited_by_count":26,"area":null},{"id":"2303.14167","title":"UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields","created":"2023-03-24","cited_by_count":26,"area":null},{"id":"2312.16648","title":"LIP-Loc: LiDAR Image Pretraining for Cross-Modal Localization","created":"2023-12-27","cited_by_count":26,"area":null},{"id":"2404.09748","title":"LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives","created":"2024-04-15","cited_by_count":26,"area":null},{"id":"2404.09833","title":"Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video","created":"2024-04-15","cited_by_count":26,"area":null},{"id":"2212.04245","title":"Domain generalization of 3D semantic segmentation in autonomous driving","created":"2022-12-07","cited_by_count":25,"area":null},{"id":"2303.01212","title":"Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review","created":"2023-03-02","cited_by_count":25,"area":"driving"},{"id":"2407.02945","title":"VEGS: View Extrapolation of Urban Scenes in 3D Gaussian Splatting using Learned Priors","created":"2024-07-03","cited_by_count":25,"area":null}],"next_cursor":"100"}