{"total":90,"rows":[{"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":"2412.04384","title":"GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction","created":"2024-12-05","cited_by_count":86,"area":null},{"id":"2412.10373","title":"GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction","created":"2024-12-13","cited_by_count":67,"area":"wm"},{"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":"2312.03774","title":"OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries","created":"2023-12-06","cited_by_count":48,"area":null},{"id":"2412.13193","title":"GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding","created":"2024-12-17","cited_by_count":46,"area":null},{"id":"2510.04333","title":"RAP: 3D Rasterization Augmented End-to-End Planning","created":"2025-10-05","cited_by_count":41,"area":"driving"},{"id":"2312.05752","title":"Camera-based 3D Semantic Scene Completion with Sparse Guidance Network","created":"2023-12-10","cited_by_count":40,"area":null},{"id":"2407.04049","title":"Occupancy as Set of Points","created":"2024-07-04","cited_by_count":38,"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":"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":"2402.07635","title":"Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles","created":"2024-02-12","cited_by_count":33,"area":null},{"id":"2311.17084","title":"DepthSSC: Monocular 3D Semantic Scene Completion via Depth-Spatial Alignment and Voxel Adaptation","created":"2023-11-28","cited_by_count":32,"area":null},{"id":"2403.01644","title":"OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Prediction","created":"2024-03-03","cited_by_count":32,"area":null},{"id":"2404.15014","title":"OccGen: Generative Multi-modal 3D Occupancy Prediction for Autonomous Driving","created":"2024-04-23","cited_by_count":29,"area":"wm"},{"id":"2405.02595","title":"Vision-based 3D occupancy prediction in autonomous driving: a review and outlook","created":"2024-05-04","cited_by_count":29,"area":null},{"id":"2502.17288","title":"GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow","created":"2025-02-24","cited_by_count":24,"area":null},{"id":"2504.19749","title":"STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow Prediction","created":"2025-04-28","cited_by_count":23,"area":null},{"id":"2402.12792","title":"OccFlowNet: Towards Self-supervised Occupancy Estimation via Differentiable Rendering and Occupancy Flow","created":"2024-02-20","cited_by_count":22,"area":null},{"id":"2502.05040","title":"GaussRender: Learning 3D Occupancy with Gaussian Rendering","created":"2025-02-07","cited_by_count":18,"area":null},{"id":"2407.17310","title":"LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Rendering","created":"2024-07-24","cited_by_count":16,"area":null},{"id":"2505.10685","title":"GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attention","created":"2025-05-15","cited_by_count":14,"area":null},{"id":"2506.04623","title":"VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2403.08504","title":"Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving","created":"2024-03-13","cited_by_count":12,"area":null},{"id":"2409.19987","title":"OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity","created":"2024-09-30","cited_by_count":9,"area":null},{"id":"2412.00932","title":"FIction: 4D Future Interaction Prediction from Video","created":"2024-12-01","cited_by_count":9,"area":null},{"id":"2503.15185","title":"3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation","created":"2025-03-19","cited_by_count":9,"area":null},{"id":"2508.02261","title":"SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completion","created":"2025-08-04","cited_by_count":9,"area":null},{"id":"2503.12369","title":"L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Model","created":"2025-03-16","cited_by_count":8,"area":null},{"id":"2507.08555","title":"Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion","created":"2025-07-11","cited_by_count":7,"area":null},{"id":"2507.19188","title":"VisHall3D: Monocular Semantic Scene Completion from Reconstructing the Visible Regions to Hallucinating the Invisible Regions","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2409.18026","title":"ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learning","created":"2024-09-26","cited_by_count":6,"area":null},{"id":"2412.05976","title":"LightOcc: Lightweight Spatial Embedding for Efficient Vision-based 3D Occupancy Prediction","created":"2024-12-08","cited_by_count":6,"area":null},{"id":"2503.06219","title":"VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene Completion","created":"2025-03-08","cited_by_count":6,"area":null},{"id":"2511.15396","title":"ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimation","created":"2025-11-19","cited_by_count":6,"area":null},{"id":"2512.20770","title":"OccuFly: A 3D Vision Benchmark for Semantic Scene Completion from the Aerial Perspective","created":"2025-12-23","cited_by_count":5,"area":null},{"id":"2411.16129","title":"Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completion","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2412.11409","title":"Multi-modal and Multi-scale Spatial Environment Understanding for Immersive Visual Text-to-Speech","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2509.16552","title":"ST-GS: Vision-Based 3D Semantic Occupancy Prediction with Spatial-Temporal Gaussian Splatting","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2511.13032","title":"Uni-Inter: Unifying 3D Human Motion Synthesis Across Diverse Interaction Contexts","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2512.05988","title":"VG3T: Visual Geometry Grounded Gaussian Transformer","created":"2025-11-28","cited_by_count":4,"area":null},{"id":"2410.11019","title":"ET-Former: Efficient Triplane Deformable Attention for 3D Semantic Scene Completion From Monocular Camera","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2502.02334","title":"Event-aided Semantic Scene Completion","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2502.14520","title":"Learning Temporal 3D Semantic Scene Completion via Optical Flow Guidance","created":"2025-02-20","cited_by_count":3,"area":null},{"id":"2503.06569","title":"Global-Aware Monocular Semantic Scene Completion with State Space Models","created":"2025-03-09","cited_by_count":3,"area":"ssm"},{"id":"2503.16825","title":"SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion","created":"2025-03-21","cited_by_count":3,"area":null},{"id":"2506.20671","title":"IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2507.13801","title":"One Step Closer: Creating the Future to Boost Monocular Semantic Scene Completion","created":"2025-07-18","cited_by_count":3,"area":null},{"id":"2507.18522","title":"GaussianFusionOcc: A Seamless Sensor Fusion Approach for 3D Occupancy Prediction Using 3D Gaussians","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2512.18363","title":"Enhancing 3D Semantic Scene Completion with a Refinement Module","created":"2025-12-20","cited_by_count":3,"area":null},{"id":"2603.25494","title":"AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2408.10618","title":"OMEGA: Efficient Occlusion-Aware Navigation for Air-Ground Robot in Dynamic Environments via State Space Model","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2503.06222","title":"Vision-based 3D Semantic Scene Completion via Capture Dynamic Representations","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2503.08485","title":"Test-Time 3D Occupancy Prediction","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2506.21185","title":"Out-of-Distribution Semantic Occupancy Prediction","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2508.13601","title":"Unleashing Semantic and Geometric Priors for 3D Scene Completion","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2508.15650","title":"Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidance","created":"2025-08-21","cited_by_count":2,"area":null},{"id":"2510.19766","title":"SEA: Semantic Map Prediction for Active Exploration of Uncertain Areas","created":"2025-10-22","cited_by_count":2,"area":"deeprl"},{"id":"2512.00300","title":"TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion","created":"2025-11-29","cited_by_count":2,"area":null},{"id":"2601.15250","title":"FlowSSC: Universal Generative Monocular Semantic Scene Completion via One-Step Latent Diffusion","created":"2026-01-21","cited_by_count":2,"area":"diffusion"},{"id":"2408.03551","title":"VPOcc: Exploiting Vanishing Point for 3D Semantic Occupancy Prediction","created":"2024-08-07","cited_by_count":1,"area":null},{"id":"2506.18266","title":"YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2509.11171","title":"SPHERE: Semantic-PHysical Engaged REpresentation for 3D Semantic Scene Completion","created":"2025-09-14","cited_by_count":1,"area":null},{"id":"2603.27238","title":"An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2605.25059","title":"VEOcc: Voxel-Centric Online Semantic Occupancy Prediction For Embodied Scene Understanding","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2405.17037","title":"BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network","created":"2024-05-27","cited_by_count":0,"area":null},{"id":"2407.03425","title":"Lift, Splat, Map: Lifting Foundation Masks for Label-Free Semantic Scene Completion","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2410.16197","title":"LASER: Script Execution by Autonomous Agents for On-demand Traffic Simulation","created":"2024-10-21","cited_by_count":0,"area":"agents"},{"id":"2502.15438","title":"Deflickering Vision-Based Occupancy Networks through Lightweight Spatio-Temporal Correlation","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2504.01023","title":"Omnidirectional Depth-Aided Occupancy Prediction based on Cylindrical Voxel for Autonomous Driving","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2504.07524","title":"DGOcc: Depth-aware Global Query-based Network for Monocular 3D Occupancy Prediction","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2505.20617","title":"OccLE: Label-Efficient 3D Semantic Occupancy Prediction","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2505.20951","title":"DSOcc: Leveraging Depth Awareness and Semantic Aid to Boost Camera-Based 3D Semantic Occupancy Prediction","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2505.23434","title":"UrbanCraft: Urban View Extrapolation via Hierarchical Sem-Geometric Priors","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2511.12498","title":"Towards Temporal Fusion Beyond the Field of View for Camera-based Semantic Scene Completion","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2511.13031","title":"Towards 3D Object-Centric Feature Learning for Semantic Scene Completion","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2512.18954","title":"VOIC: Visible-Occluded Integrated Guidance for 3D Semantic Scene Completion","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2602.03371","title":"Multi-Resolution Alignment for Voxel Sparsity in Camera-Based 3D Semantic Scene Completion","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.06488","title":"Rebenchmarking Unsupervised Monocular 3D Occupancy Prediction","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.21487","title":"GaussianSSC: Triplane-Guided Directional Gaussian Fields for 3D Semantic Completion","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.01081","title":"ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.05780","title":"Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completion","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.27578","title":"World2Minecraft: Occupancy-Driven Simulated Scenes Construction","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.28587","title":"Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.31688","title":"Semantic Occupancy Prediction with Dual Range-Voxel Representation","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.04732","title":"SparseOcc++: Geometry-Aware Sparse Latent Representation for Semantic Occupancy Prediction","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.17660","title":"RayOcc: Occlusion-Aware Ray Occupancy Estimation via Gaussian Mixture Intensity","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.08476","title":"RayLift: Lifting Complementary Ray-Wise Evidence with 3D Geometry Priors for Semantic Scene Completion","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2609.17413","title":"SSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completion","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2610.03031","title":"CrowdOcc: Monocular Semantic Scene Completion for Quadruped Robots in Crowded Indoor Environments","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}