{"list":"other","total":95,"rows":[{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"2304.14365","title":"Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving","created":"2023-04-27","cited_by_count":332},{"id":"2302.12251","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","created":"2023-02-23","cited_by_count":313},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293},{"id":"2311.16038","title":"OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving","created":"2023-11-27","cited_by_count":233},{"id":"2012.03762","title":"Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion","created":"2020-12-07","cited_by_count":223},{"id":"2303.03991","title":"OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception","created":"2023-03-07","cited_by_count":221},{"id":"2008.10559","title":"LMSCNet: Lightweight Multiscale 3D Semantic Completion","created":"2020-08-24","cited_by_count":188},{"id":"2107.06829","title":"FAST-LIO2: Fast Direct LiDAR-inertial Odometry","created":"2021-07-14","cited_by_count":183},{"id":"2405.17429","title":"GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction","created":"2024-05-27","cited_by_count":157},{"id":"2309.09502","title":"RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision","created":"2023-09-18","cited_by_count":128},{"id":"2002.09147","title":"SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances","created":"2020-02-21","cited_by_count":123},{"id":"2008.01550","title":"Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation","created":"2020-08-04","cited_by_count":112},{"id":"2404.09502","title":"SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction","created":"2024-04-15","cited_by_count":96},{"id":"2412.04384","title":"GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction","created":"2024-12-05","cited_by_count":86},{"id":"2303.06884","title":"SCPNet: Semantic Scene Completion on Point Cloud","created":"2023-03-13","cited_by_count":80},{"id":"2306.09001","title":"SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving","created":"2023-06-15","cited_by_count":75},{"id":"2412.10373","title":"GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction","created":"2024-12-13","cited_by_count":67},{"id":"2308.16896","title":"PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction","created":"2023-08-31","cited_by_count":52},{"id":"2408.11447","title":"GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting","created":"2024-08-21","cited_by_count":50},{"id":"2404.04561","title":"Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Prediction","created":"2024-04-06","cited_by_count":48},{"id":"2412.04380","title":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding","created":"2024-12-05","cited_by_count":45},{"id":"2205.05570","title":"Review on Panoramic Imaging and Its Applications in Scene Understanding","created":"2022-05-11","cited_by_count":43},{"id":"2404.11958","title":"Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation","created":"2024-04-18","cited_by_count":43},{"id":"2312.05752","title":"Camera-based 3D Semantic Scene Completion with Sparse Guidance Network","created":"2023-12-10","cited_by_count":40},{"id":"2109.11453","title":"Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds","created":"2021-09-23","cited_by_count":37},{"id":"2505.10696","title":"TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation","created":"2025-05-15","cited_by_count":36},{"id":"2306.15349","title":"SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusion","created":"2023-06-27","cited_by_count":30},{"id":"2408.09859","title":"OccMamba: Semantic Occupancy Prediction with State Space Models","created":"2024-08-19","cited_by_count":30},{"id":"2412.10734","title":"OmniHD-Scenes: A Next-Generation Multimodal Dataset for Autonomous Driving","created":"2024-12-14","cited_by_count":27},{"id":"2504.09540","title":"EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Sampler","created":"2025-04-13","cited_by_count":27},{"id":"2312.02700","title":"Revisit Human-Scene Interaction via Space Occupancy","created":"2023-12-05","cited_by_count":25},{"id":"2509.04444","title":"One Flight Over the Gap: A Survey from Perspective to Panoramic Vision","created":"2025-09-04","cited_by_count":25},{"id":"2305.16133","title":"OVO: Open-Vocabulary Occupancy","created":"2023-05-25","cited_by_count":24},{"id":"2407.07587","title":"Let Occ Flow: Self-Supervised 3D Occupancy Flow Prediction","created":"2024-07-10","cited_by_count":24},{"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},{"id":"2501.15394","title":"Doracamom: Joint 3D Detection and Occupancy Prediction with Multi-view 4D Radars and Cameras for Omnidirectional Perception","created":"2025-01-26","cited_by_count":22},{"id":"2510.15352","title":"GaussGym: An open-source real-to-sim framework for learning locomotion from pixels","created":"2025-10-17","cited_by_count":22},{"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},{"id":"2407.16197","title":"LiCROcc: Teach Radar for Accurate Semantic Occupancy Prediction using LiDAR and Camera","created":"2024-07-23","cited_by_count":19},{"id":"2504.14604","title":"RoboOcc: Enhancing the Geometric and Semantic Scene Understanding for Robots","created":"2025-04-20","cited_by_count":15},{"id":"2309.12708","title":"PointSSC: A Cooperative Vehicle-Infrastructure Point Cloud Benchmark for Semantic Scene Completion","created":"2023-09-22","cited_by_count":14},{"id":"2401.12422","title":"InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Prediction","created":"2024-01-23","cited_by_count":14},{"id":"2503.04565","title":"Omnidirectional Multi-Object Tracking","created":"2025-03-06","cited_by_count":13},{"id":"2503.09010","title":"HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots","created":"2025-03-12","cited_by_count":13},{"id":"2507.06230","title":"Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion","created":"2025-07-08","cited_by_count":13},{"id":"2206.08077","title":"Neural Scene Representation for Locomotion on Structured Terrain","created":"2022-06-16","cited_by_count":12},{"id":"2403.08504","title":"Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving","created":"2024-03-13","cited_by_count":12},{"id":"2403.08885","title":"SLCF-Net: Sequential LiDAR-Camera Fusion for Semantic Scene Completion using a 3D Recurrent U-Net","created":"2024-03-13","cited_by_count":12},{"id":"2410.15674","title":"TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight","created":"2024-10-21","cited_by_count":12},{"id":"2509.05314","title":"ManipDreamer3D : Synthesizing Plausible Robotic Manipulation Video with Occupancy-aware 3D Trajectory","created":"2025-08-29","cited_by_count":12},{"id":"2404.18225","title":"Quadruped robot traversing 3D complex environments with limited perception","created":"2024-04-28","cited_by_count":10},{"id":"2410.15792","title":"WildOcc: A Benchmark for Off-Road 3D Semantic Occupancy Prediction","created":"2024-10-21","cited_by_count":10},{"id":"2405.15170","title":"Label-efficient Semantic Scene Completion with Scribble Annotations","created":"2024-05-24","cited_by_count":9},{"id":"2409.19987","title":"OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity","created":"2024-09-30","cited_by_count":9},{"id":"2508.08240","title":"ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks","created":"2025-08-11","cited_by_count":9},{"id":"2505.05512","title":"Occupancy World Model for Robots","created":"2025-05-07","cited_by_count":8},{"id":"2505.19214","title":"Omni-Perception: Omnidirectional Collision Avoidance for Legged Locomotion in Dynamic Environments","created":"2025-05-25","cited_by_count":8},{"id":"2509.08388","title":"Semantic Causality-Aware Vision-Based 3D Occupancy Prediction","created":"2025-09-10","cited_by_count":8},{"id":"2510.16500","title":"Advancing Off-Road Autonomous Driving: The Large-Scale ORAD-3D Dataset and Comprehensive Benchmarks","created":"2025-10-18","cited_by_count":8},{"id":"2507.08555","title":"Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion","created":"2025-07-11","cited_by_count":7},{"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},{"id":"2403.11607","title":"AGRNav: Efficient and Energy-Saving Autonomous Navigation for Air-Ground Robots in Occlusion-Prone Environments","created":"2024-03-18","cited_by_count":6},{"id":"2502.07183","title":"Space-Aware Instruction Tuning: Dataset and Benchmark for Guide Dog Robots Assisting the Visually Impaired","created":"2025-02-11","cited_by_count":6},{"id":"2211.11293","title":"Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent Transformer","created":"2022-11-21","cited_by_count":5},{"id":"2409.11975","title":"Particle-based Instance-aware Semantic Occupancy Mapping in Dynamic Environments","created":"2024-09-18","cited_by_count":5},{"id":"2410.09886","title":"Point Cloud Mixture-of-Domain-Experts Model for 3D Self-supervised Learning","created":"2024-10-13","cited_by_count":5},{"id":"2505.03284","title":"OccCylindrical: Multi-Modal Fusion with Cylindrical Representation for 3D Semantic Occupancy Prediction","created":"2025-05-06","cited_by_count":5},{"id":"2507.20217","title":"Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots","created":"2025-07-27","cited_by_count":5},{"id":"2403.12039","title":"StereoNavNet: Learning to Navigate using Stereo Cameras with Auxiliary Occupancy Voxels","created":"2024-03-18","cited_by_count":4},{"id":"2406.16578","title":"QuadrupedGPT: Towards a Versatile Quadruped Agent in Open-ended Worlds","created":"2024-06-24","cited_by_count":4},{"id":"2501.17594","title":"Watch Your STEPP: Semantic Traversability Estimation using Pose Projected Features","created":"2025-01-29","cited_by_count":4},{"id":"2509.20036","title":"MARG: MAstering Risky Gap Terrains for Legged Robots with Elevation Mapping","created":"2025-09-24","cited_by_count":4},{"id":"2412.03353","title":"MOVE: Multi-skill Omnidirectional Legged Locomotion with Limited View in 3D Environments","created":"2024-12-04","cited_by_count":3},{"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},{"id":"2502.02334","title":"Event-aided Semantic Scene Completion","created":"2025-02-04","cited_by_count":3},{"id":"2110.04426","title":"Vision-based Navigation for a Small-scale Quadruped Robot Pegasus-Mini","created":"2021-10-09","cited_by_count":2},{"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},{"id":"2411.17134","title":"TRIP: Terrain Traversability Mapping With Risk-Aware Prediction for Enhanced Online Quadrupedal Robot Navigation","created":"2024-11-26","cited_by_count":2},{"id":"2502.12655","title":"LiMo-Calib: On-Site Fast LiDAR-Motor Calibration for Quadruped Robot-Based Panoramic 3D Sensing System","created":"2025-02-18","cited_by_count":2},{"id":"2506.02286","title":"Efficient Manipulation-Enhanced Semantic Mapping With Uncertainty-Informed Action Selection","created":"2025-06-02","cited_by_count":2},{"id":"2506.19781","title":"The Starlink Robot: A Platform and Dataset for Mobile Satellite Communication","created":"2025-06-24","cited_by_count":2},{"id":"2505.14859","title":"A Hierarchical Graph-Based Terrain-Aware Autonomous Navigation Approach for Complementary Multimodal Ground-Aerial Exploration","created":"2025-05-20","cited_by_count":1},{"id":"2510.01592","title":"Real-time Multi-Plane Segmentation Based on GPU Accelerated High-Resolution 3D Voxel Mapping for Legged Robot Locomotion","created":"2025-10-02","cited_by_count":1}],"next_cursor":null}