{"total":86,"rows":[{"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":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209,"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":"2309.09502","title":"RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision","created":"2023-09-18","cited_by_count":128,"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":"2312.01919","title":"COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction","created":"2023-12-04","cited_by_count":96,"area":null},{"id":"2306.15670","title":"Symphonize 3D Semantic Scene Completion with Contextual Instance Queries","created":"2023-06-27","cited_by_count":90,"area":null},{"id":"2412.04384","title":"GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction","created":"2024-12-05","cited_by_count":86,"area":null},{"id":"2403.07773","title":"SemCity: Semantic Scene Generation with Triplane Diffusion","created":"2024-03-12","cited_by_count":53,"area":"diffusion"},{"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":"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":"2405.04299","title":"ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers","created":"2024-05-07","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":"2305.15694","title":"Learning Occupancy for Monocular 3D Object Detection","created":"2023-05-25","cited_by_count":36,"area":null},{"id":"2308.07234","title":"UniWorld: Autonomous Driving Pre-training via World Models","created":"2023-08-14","cited_by_count":33,"area":"wm"},{"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":"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":"2310.07522","title":"S4C: Self-Supervised Semantic Scene Completion with Neural Fields","created":"2023-10-11","cited_by_count":28,"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":"2305.16133","title":"OVO: Open-Vocabulary Occupancy","created":"2023-05-25","cited_by_count":24,"area":null},{"id":"2401.08045","title":"Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities","created":"2024-01-16","cited_by_count":24,"area":"driving"},{"id":"2409.13430","title":"CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction","created":"2024-09-20","cited_by_count":24,"area":null},{"id":"2405.08816","title":"The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition","created":"2024-05-14","cited_by_count":23,"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":"2407.12294","title":"VEON: Vocabulary-Enhanced Occupancy Prediction","created":"2024-07-17","cited_by_count":22,"area":null},{"id":"2409.07972","title":"Deep Height Decoupling for Precise Vision-based 3D Occupancy Prediction","created":"2024-09-12","cited_by_count":16,"area":null},{"id":"2411.00340","title":"GAFusion: Adaptive Fusing LiDAR and Camera with Multiple Guidance for 3D Object Detection","created":"2024-11-01","cited_by_count":15,"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":"2306.12681","title":"One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception","created":"2023-06-22","cited_by_count":13,"area":null},{"id":"2403.05329","title":"OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction","created":"2024-03-08","cited_by_count":13,"area":null},{"id":"2507.06230","title":"Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion","created":"2025-07-08","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":"2404.03658","title":"Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning","created":"2024-04-04","cited_by_count":12,"area":null},{"id":"2403.14366","title":"SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field","created":"2024-03-21","cited_by_count":10,"area":null},{"id":"2506.05563","title":"VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction","created":"2025-06-05","cited_by_count":10,"area":null},{"id":"2308.13794","title":"SOGDet: Semantic-Occupancy Guided Multi-view 3D Object Detection","created":"2023-08-26","cited_by_count":9,"area":null},{"id":"2406.07037","title":"PanoSSC: Exploring Monocular Panoptic 3D Scene Reconstruction for Autonomous Driving","created":"2024-06-11","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":"2504.18424","title":"LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning","created":"2025-04-25","cited_by_count":8,"area":null},{"id":"2411.03696","title":"OccLoff: Learning Optimized Feature Fusion for 3D Occupancy Prediction","created":"2024-11-06","cited_by_count":7,"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":"2402.18140","title":"OccTransformer: Improving BEVFormer for 3D camera-only occupancy prediction","created":"2024-02-28","cited_by_count":6,"area":null},{"id":"2411.05311","title":"ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving","created":"2024-11-08","cited_by_count":6,"area":null},{"id":"2308.16160","title":"Occ$^2$Net: Robust Image Matching Based on 3D Occupancy Estimation for Occluded Regions","created":"2023-08-14","cited_by_count":5,"area":null},{"id":"2408.11559","title":"Semi-supervised 3D Semantic Scene Completion with 2D Vision Foundation Model Guidance","created":"2024-08-21","cited_by_count":5,"area":null},{"id":"2412.13569","title":"Multi-View Pedestrian Occupancy Prediction with a Novel Synthetic Dataset","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2601.22729","title":"GaussianOcc3D: A Gaussian-Based Adaptive Multi-modal 3D Occupancy Prediction","created":"2026-01-30","cited_by_count":5,"area":"ssm"},{"id":"2603.05711","title":"Any to Full: Prompting Depth Anything for Depth Completion in One Stage","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2307.07938","title":"CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion","created":"2023-07-16","cited_by_count":4,"area":null},{"id":"2402.04671","title":"V2VSSC: A 3D Semantic Scene Completion Benchmark for Perception with Vehicle to Vehicle Communication","created":"2024-02-07","cited_by_count":4,"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":"2507.07374","title":"PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2305.16829","title":"BEV-IO: Enhancing Bird's-Eye-View 3D Detection with Instance Occupancy","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2503.16825","title":"SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion","created":"2025-03-21","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":"2309.08504","title":"OccupancyDETR: Using DETR for Mixed Dense-sparse 3D Occupancy Prediction","created":"2023-09-15","cited_by_count":2,"area":null},{"id":"2504.15888","title":"MS-Occ: Multi-Stage LiDAR-Camera Fusion for 3D Semantic Occupancy Prediction","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2511.17221","title":"QueryOcc: Query-based Self-Supervision for 3D Semantic Occupancy","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2307.05873","title":"OG: Equip vision occupancy with instance segmentation and visual grounding","created":"2023-07-12","cited_by_count":1,"area":null},{"id":"2408.13454","title":"AdaOcc: Adaptive-Resolution Occupancy Prediction","created":"2024-08-24","cited_by_count":1,"area":null},{"id":"2501.09954","title":"AIRCHITECT v2: Learning the Hardware Accelerator Design Space through Unified Representations","created":"2025-01-17","cited_by_count":1,"area":null},{"id":"2507.23599","title":"DA-Occ: Direction-Aware 2D Convolution for Efficient and Geometry-Preserving 3D Occupancy Prediction in Autonomous Driving","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2508.01197","title":"A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding","created":"2025-08-02","cited_by_count":1,"area":null},{"id":"2508.02323","title":"Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single Images","created":"2025-08-04","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":"2510.12362","title":"CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2511.16949","title":"MobileOcc: A Human-Aware Semantic Occupancy Dataset for Mobile Robots","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2603.22852","title":"Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2606.22971","title":"Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AI","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2609.09012","title":"Spheriverse: 3D Scene Understanding from Spherical Observations in the Wild","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2412.07163","title":"Fast Occupancy Network","created":"2024-12-10","cited_by_count":0,"area":null},{"id":"2506.06296","title":"Dynamic Graph CNN with Jacobi Kolmogorov-Arnold Networks for 3D Classification of Point Sets","created":"2025-05-17","cited_by_count":0,"area":null},{"id":"2507.20963","title":"GTAD: Global Temporal Aggregation Denoising Learning for 3D Semantic Occupancy Prediction","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2511.07925","title":"HD$^2$-SSC: High-Dimension High-Density Semantic Scene Completion for Autonomous Driving","created":"2025-11-11","cited_by_count":0,"area":"driving"},{"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":"2512.04734","title":"MT-Depth: Multi-task Instance feature analysis for the Depth Completion","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2512.05783","title":"Curvature-Regularized Variational Autoencoder for 3D Scene Reconstruction from Sparse Depth","created":"2025-12-05","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":"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":"2606.03581","title":"UnsOcc: 3D Semantic Occupancy Prediction in Unstructured Scene via Rendering Fusion","created":"2026-06-02","cited_by_count":0,"area":null}],"next_cursor":null}