{"total":472,"rows":[{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592,"area":null},{"id":"2312.10035","title":"Point Transformer V3: Simpler, Faster, Stronger","created":"2023-12-15","cited_by_count":589,"area":null},{"id":"2210.05666","title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","created":"2022-10-11","cited_by_count":388,"area":null},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366,"area":null},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363,"area":null},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336,"area":null},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329,"area":null},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316,"area":null},{"id":"2302.12251","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","created":"2023-02-23","cited_by_count":313,"area":null},{"id":"1811.10092","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","created":"2018-11-25","cited_by_count":305,"area":"offlinerl"},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293,"area":null},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261,"area":null},{"id":"2303.16196","title":"SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis","created":"2023-03-28","cited_by_count":247,"area":null},{"id":"2303.03991","title":"OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception","created":"2023-03-07","cited_by_count":221,"area":null},{"id":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209,"area":null},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200,"area":null},{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179,"area":null},{"id":"2207.04397","title":"2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds","created":"2022-07-10","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":"2306.09310","title":"Infinite Photorealistic Worlds using Procedural Generation","created":"2023-06-15","cited_by_count":147,"area":null},{"id":"2311.12754","title":"SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction","created":"2023-11-21","cited_by_count":133,"area":null},{"id":"2105.01905","title":"4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface","created":"2021-05-05","cited_by_count":124,"area":null},{"id":"2111.13260","title":"NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes","created":"2021-11-25","cited_by_count":119,"area":null},{"id":"2203.12667","title":"Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions","created":"2022-03-22","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":"2210.05494","title":"Map-free Visual Relocalization: Metric Pose Relative to a Single Image","created":"2022-10-11","cited_by_count":114,"area":null},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110,"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":"2404.09502","title":"SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction","created":"2024-04-15","cited_by_count":96,"area":null},{"id":"2103.14326","title":"Bidirectional Projection Network for Cross Dimension Scene Understanding","created":"2021-03-26","cited_by_count":95,"area":null},{"id":"2203.09283","title":"PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation","created":"2022-03-17","cited_by_count":95,"area":null},{"id":"2207.11514","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","created":"2022-07-23","cited_by_count":95,"area":"mllm"},{"id":"2102.03550","title":"UniFuse: Unidirectional Fusion for 360$^{\\circ}$ Panorama Depth Estimation","created":"2021-02-06","cited_by_count":92,"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":"2309.14616","title":"NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space","created":"2023-09-26","cited_by_count":90,"area":null},{"id":"2104.02416","title":"Variational Transformer Networks for Layout Generation","created":"2021-04-06","cited_by_count":88,"area":null},{"id":"2110.08188","title":"Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation","created":"2021-10-15","cited_by_count":87,"area":null},{"id":"2404.02838","title":"I-Design: Personalized LLM Interior Designer","created":"2024-04-03","cited_by_count":87,"area":null},{"id":"2302.13540","title":"OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion","created":"2023-02-27","cited_by_count":86,"area":null},{"id":"2308.09718","title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training","created":"2023-08-18","cited_by_count":86,"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":"2412.08376","title":"Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization","created":"2024-12-11","cited_by_count":82,"area":null},{"id":"2303.06884","title":"SCPNet: Semantic Scene Completion on Point Cloud","created":"2023-03-13","cited_by_count":80,"area":"distill"},{"id":"2211.03017","title":"Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing","created":"2022-11-06","cited_by_count":78,"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":"2103.07466","title":"3D Semantic Scene Completion: a Survey","created":"2021-03-12","cited_by_count":74,"area":null},{"id":"2308.04758","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","created":"2023-08-09","cited_by_count":72,"area":null},{"id":"2301.08247","title":"Multiview Compressive Coding for 3D Reconstruction","created":"2023-01-19","cited_by_count":71,"area":null},{"id":"2111.02444","title":"Panoptic 3D Scene Reconstruction From a Single RGB Image","created":"2021-11-03","cited_by_count":70,"area":null},{"id":"2208.07227","title":"DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images","created":"2022-08-15","cited_by_count":69,"area":null},{"id":"2408.14197","title":"Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving","created":"2024-08-26","cited_by_count":69,"area":"wm"},{"id":"1902.07742","title":"From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following","created":"2019-02-20","cited_by_count":67,"area":"offlinerl"},{"id":"2301.04545","title":"AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers","created":"2023-01-11","cited_by_count":67,"area":null},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67,"area":"wm"},{"id":"2103.14025","title":"The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI","created":"2021-03-25","cited_by_count":65,"area":null},{"id":"2106.14490","title":"Making Images Real Again: A Comprehensive Survey on Deep Image Composition","created":"2021-06-28","cited_by_count":63,"area":null},{"id":"2403.14158","title":"Volumetric Environment Representation for Vision-Language Navigation","created":"2024-03-21","cited_by_count":63,"area":null},{"id":"2206.08423","title":"IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes","created":"2022-06-16","cited_by_count":62,"area":null},{"id":"2110.11325","title":"Learning 3D Semantic Segmentation with only 2D Image Supervision","created":"2021-10-21","cited_by_count":60,"area":null},{"id":"2410.20030","title":"SCube: Instant Large-Scale Scene Reconstruction using VoxSplats","created":"2024-10-26","cited_by_count":60,"area":"diffusion"},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56,"area":null},{"id":"2303.14191","title":"Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning","created":"2023-03-24","cited_by_count":56,"area":null},{"id":"2404.11613","title":"InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior","created":"2024-04-17","cited_by_count":56,"area":"diffusion"},{"id":"2104.03640","title":"Semantic Scene Completion via Integrating Instances and Scene in-the-Loop","created":"2021-04-08","cited_by_count":55,"area":null},{"id":"2403.07773","title":"SemCity: Semantic Scene Generation with Triplane Diffusion","created":"2024-03-12","cited_by_count":53,"area":"diffusion"},{"id":"2308.08947","title":"Watch Your Steps: Local Image and Scene Editing by Text Instructions","created":"2023-08-17","cited_by_count":50,"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":"2103.05558","title":"Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis","created":"2021-03-09","cited_by_count":49,"area":null},{"id":"2304.12205","title":"Synthetic Datasets for Autonomous Driving: A Survey","created":"2023-04-24","cited_by_count":48,"area":null},{"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,"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":"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":"2403.14418","title":"OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation","created":"2024-03-21","cited_by_count":44,"area":null},{"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,"area":"distill"},{"id":"2102.12321","title":"AGENT: A Benchmark for Core Psychological Reasoning","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2312.02158","title":"PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness","created":"2023-12-04","cited_by_count":42,"area":null},{"id":"2103.14644","title":"Planar Surface Reconstruction from Sparse Views","created":"2021-03-26","cited_by_count":40,"area":null},{"id":"2203.07060","title":"MotionSC: Data Set and Network for Real-Time Semantic Mapping in Dynamic Environments","created":"2022-03-14","cited_by_count":40,"area":"wm"},{"id":"2304.09677","title":"Reference-guided Controllable Inpainting of Neural Radiance Fields","created":"2023-04-19","cited_by_count":40,"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":"2403.13470","title":"Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion","created":"2024-03-20","cited_by_count":40,"area":"wm"},{"id":"2302.10237","title":"SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry","created":"2023-02-16","cited_by_count":39,"area":null},{"id":"2105.08612","title":"SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data","created":"2021-05-18","cited_by_count":38,"area":null},{"id":"2205.10468","title":"Deep Learning for Omnidirectional Vision: A Survey and New Perspectives","created":"2022-05-21","cited_by_count":38,"area":null},{"id":"2407.04049","title":"Occupancy as Set of Points","created":"2024-07-04","cited_by_count":38,"area":null},{"id":"2601.05640","title":"SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving","created":"2026-01-09","cited_by_count":38,"area":"mllm"},{"id":"2109.11453","title":"Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds","created":"2021-09-23","cited_by_count":37,"area":null},{"id":"2112.03842","title":"A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyond","created":"2021-12-07","cited_by_count":37,"area":null},{"id":"2303.11616","title":"HRDFuse: Monocular 360{\\deg}Depth Estimation by Collaboratively Learning Holistic-with-Regional Depth Distributions","created":"2023-03-21","cited_by_count":37,"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":"1805.12573","title":"Learning a Prior over Intent via Meta-Inverse Reinforcement Learning","created":"2018-05-31","cited_by_count":36,"area":"offlinerl"},{"id":"2209.02952","title":"BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation","created":"2022-09-07","cited_by_count":35,"area":null},{"id":"2306.16329","title":"DiffComplete: Diffusion-based Generative 3D Shape Completion","created":"2023-06-28","cited_by_count":35,"area":"diffusion"},{"id":"2108.11544","title":"Vision-Language Navigation: A Survey and Taxonomy","created":"2021-08-26","cited_by_count":34,"area":null},{"id":"2110.04955","title":"BuildingNet: Learning to Label 3D Buildings","created":"2021-10-11","cited_by_count":33,"area":null},{"id":"2301.00527","title":"Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data","created":"2023-01-02","cited_by_count":33,"area":"diffusion"},{"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"}],"next_cursor":"100"}