{"total":135,"rows":[{"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":"2408.11447","title":"GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting","created":"2024-08-21","cited_by_count":50,"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":"2412.04380","title":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding","created":"2024-12-05","cited_by_count":45,"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":"2512.16919","title":"DVGT: Driving Visual Geometry Transformer","created":"2025-12-18","cited_by_count":21,"area":null},{"id":"2411.07725","title":"ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictions","created":"2024-11-12","cited_by_count":20,"area":null},{"id":"2506.10977","title":"QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction","created":"2025-06-12","cited_by_count":20,"area":null},{"id":"2410.18979","title":"PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views","created":"2024-10-24","cited_by_count":19,"area":null},{"id":"2502.05040","title":"GaussRender: Learning 3D Occupancy with Gaussian Rendering","created":"2025-02-07","cited_by_count":18,"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":"2411.14716","title":"VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving","created":"2024-11-22","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":"2411.12452","title":"GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous Driving","created":"2024-11-19","cited_by_count":11,"area":null},{"id":"2507.19451","title":"GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting","created":"2025-07-25","cited_by_count":11,"area":null},{"id":"2602.21552","title":"Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Prediction","created":"2026-02-25","cited_by_count":11,"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":"2511.04595","title":"UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstruction","created":"2025-11-06","cited_by_count":10,"area":null},{"id":"2504.12959","title":"Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2507.19856","title":"RaGS: Unleashing 3D Gaussian Splatting from 4D Radar and Monocular Cues for 3D Object Detection","created":"2025-07-26","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":"2501.16684","title":"SliceOcc: Indoor 3D Semantic Occupancy Prediction with Vertical Slice Representation","created":"2025-01-28","cited_by_count":8,"area":null},{"id":"2508.13995","title":"Self-Supervised Sparse Sensor Fusion for Long Range Perception","created":"2025-08-19","cited_by_count":8,"area":null},{"id":"2509.08388","title":"Semantic Causality-Aware Vision-Based 3D Occupancy Prediction","created":"2025-09-10","cited_by_count":8,"area":null},{"id":"2511.03571","title":"OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Camera","created":"2025-11-05","cited_by_count":8,"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":"2412.14579","title":"GSRender: Deduplicated Occupancy Prediction via Weakly Supervised 3D Gaussian Splatting","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2509.08302","title":"Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities","created":"2025-09-10","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":"2603.23502","title":"OccAny: Generalized Unconstrained Urban 3D Occupancy","created":"2026-03-24","cited_by_count":6,"area":null},{"id":"2602.22667","title":"Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes","created":"2026-02-26","cited_by_count":5,"area":null},{"id":"2603.06210","title":"VG3S: Visual Geometry Grounded Gaussian Splatting for Semantic Occupancy Prediction","created":"2026-03-06","cited_by_count":5,"area":null},{"id":"2603.13108","title":"Panoramic Multimodal Semantic Occupancy Prediction for Quadruped Robots","created":"2026-03-13","cited_by_count":5,"area":null},{"id":"2504.04732","title":"Inverse++: Vision-Centric 3D Semantic Occupancy Prediction Assisted with 3D Object Detection","created":"2025-04-07","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":"2509.16588","title":"SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2510.04759","title":"Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction","created":"2025-10-06","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":"2412.18884","title":"HV-BEV: Decoupling Horizontal and Vertical Feature Sampling for Multi-View 3D Object Detection","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2501.15384","title":"MetaOcc: Spatio-Temporal Fusion of Surround-View 4D Radar and Camera for 3D Occupancy Prediction with Dual Training Strategies","created":"2025-01-26","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":"2503.16825","title":"SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion","created":"2025-03-21","cited_by_count":3,"area":null},{"id":"2506.09417","title":"ODG: Occupancy Prediction Using Dual Gaussians","created":"2025-06-11","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":"2508.10936","title":"Vision-Only Gaussian Splatting for Collaborative Semantic Occupancy Prediction","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2509.16119","title":"RadarGaussianDet3D: Gaussian Representation-based Real-time 3D Object Detection with 4D Automotive Radars","created":"2025-09-19","cited_by_count":3,"area":null},{"id":"2512.03370","title":"ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-based 3D Scene Understanding","created":"2025-12-03","cited_by_count":3,"area":null},{"id":"2602.23172","title":"Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking","created":"2026-02-26","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":"2406.03394","title":"Gaussian Primitives for Deformable Image Registration","created":"2024-06-05","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":"2504.02270","title":"MinkOcc: Towards real-time label-efficient semantic occupancy prediction","created":"2025-04-03","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":"2505.09562","title":"Camera-Only 3D Panoptic Scene Completion for Autonomous Driving through Differentiable Object Shapes","created":"2025-05-14","cited_by_count":2,"area":null},{"id":"2506.14825","title":"GraphGSOcc: Semantic-Geometric Graph Transformer with Dynamic-Static Decoupling for 3D Gaussian Splatting-based Occupancy Prediction","created":"2025-06-13","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":"2509.26087","title":"Easy3D-Labels: Supervising Semantic Occupancy Estimation with 3D Pseudo-Labels for Automotive Perception","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.12174","title":"UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering","created":"2025-10-14","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":"2512.00300","title":"TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion","created":"2025-11-29","cited_by_count":2,"area":null},{"id":"2601.02339","title":"Joint Semantic and Rendering Enhancements in 3D Gaussian Modeling with Anisotropic Local Encoding","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2603.12144","title":"O3N: Omnidirectional Open-Vocabulary Occupancy Prediction for Embodied Intelligent Robotics","created":"2026-03-12","cited_by_count":2,"area":null},{"id":"2604.28115","title":"FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Prediction","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2607.09629","title":"4DR360: State Reasoning for Joint 3D Detection and Occupancy Prediction in 4D Radar-Camera Full-Scene Perception","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2608.30657","title":"InfraOcc: An Infrastructure Occupancy Benchmark with Static-to-Dynamic Reasoning","created":"2026-08-31","cited_by_count":2,"area":null},{"id":"2503.09941","title":"TGP: Two-modal occupancy prediction with 3D Gaussian and sparse points for 3D Environment Awareness","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2506.05473","title":"S2GO: Streaming Sparse Gaussian Occupancy Prediction","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2506.07002","title":"BePo: Dual Representation for 3D Occupancy Prediction","created":"2025-06-08","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":"2506.23565","title":"OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Driving","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2508.11183","title":"Versatile Video Representation via Feed-Forward 2D Gaussian Splatting Tokenization","created":"2025-08-15","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":"2601.15644","title":"SuperOcc: Toward Cohesive Temporal Modeling for Superquadric-based 3D Occupancy Prediction","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2603.04254","title":"EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding","created":"2026-03-04","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":"2603.27238","title":"An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2605.16911","title":"VGGT-Occ: Geometry-Grounded and Density-Aware Gated Fusion for 3D Occupancy Prediction","created":"2026-05-16","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":"2606.16960","title":"SurroundNEXO: Ego-Centric Metric Bridging for Spatially Consistent Geometry in Autonomous Driving","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2606.21373","title":"FLM-Occ: Feed-forward Likelihood Maximization for Efficient Indoor Occupancy Prediction","created":"2026-06-19","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":"2607.01633","title":"Bridging 3D Gaussians and Semantic Occupancy for Comprehensive Open-Vocabulary Scene Understanding from Unposed Images","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.01928","title":"Sparse-Aware Vector Quantization for Bandwidth-Efficient Collaborative 3D Semantic Occupancy Prediction","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.18078","title":"VGOcc: Learning Visual-Geometric Gaussians for Vision-Centric 3D Driving Occupancy Prediction","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2609.04411","title":"AquaBEV: Monocular Underwater BEV Occupancy with 3D Sonar Supervision","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2410.13864","title":"UniDrive: Towards Universal Driving Perception Across Camera Configurations","created":"2024-10-17","cited_by_count":0,"area":null},{"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":"2503.04863","title":"Manboformer: Learning Gaussian Representations via Spatial-temporal Attention Mechanism","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2503.22087","title":"Streaming Dense Voxel Representations for 3D Occupancy Prediction","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2505.12693","title":"TACOcc:Target-Adaptive Cross-Modal Fusion with Volume Rendering for 3D Semantic Occupancy","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2505.15294","title":"R3GS: Gaussian Splatting for Robust Reconstruction and Relocalization in Unconstrained Image Collections","created":"2025-05-21","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":"2507.13387","title":"From Binary to Semantic: Utilizing Large-Scale Binary Occupancy Data for 3D Semantic Occupancy Prediction","created":"2025-07-16","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":"2511.17361","title":"SuperQuadricOcc: Real-Time Self-Supervised Semantic Occupancy Estimation with Superquadric Volume Rendering","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2602.06400","title":"TFusionOcc: T-Primitive Based Object-Centric Multi-Sensor Fusion Framework for 3D Occupancy Prediction","created":"2026-02-06","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":"2602.16385","title":"Adaptive Multi-Scale Channel-Spatial Attention Aggregation Framework for 3D Indoor Semantic Scene Completion Toward Assisting Visually Impaired","created":"2026-02-18","cited_by_count":0,"area":null}],"next_cursor":"100"}