{"total":389,"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":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559,"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":"2108.08839","title":"PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers","created":"2021-08-19","cited_by_count":286,"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":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231,"area":null},{"id":"2101.02691","title":"Self-Supervised Pretraining of 3D Features on any Point-Cloud","created":"2021-01-07","cited_by_count":217,"area":null},{"id":"2406.11824","title":"Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation","created":"2024-06-17","cited_by_count":137,"area":null},{"id":"2305.14093","title":"Weakly Supervised 3D Open-vocabulary Segmentation","created":"2023-05-23","cited_by_count":135,"area":null},{"id":"2312.10671","title":"Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance","created":"2023-12-17","cited_by_count":124,"area":null},{"id":"2112.13762","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","created":"2021-12-27","cited_by_count":122,"area":null},{"id":"2107.04286","title":"Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset","created":"2021-07-09","cited_by_count":118,"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":"2311.12058","title":"FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin","created":"2023-11-18","cited_by_count":103,"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":"2102.03550","title":"UniFuse: Unidirectional Fusion for 360$^{\\circ}$ Panorama Depth Estimation","created":"2021-02-06","cited_by_count":92,"area":null},{"id":"2104.02246","title":"One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation","created":"2021-04-06","cited_by_count":89,"area":null},{"id":"2108.10528","title":"ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation","created":"2021-08-24","cited_by_count":77,"area":null},{"id":"2105.13509","title":"Learning to Stylize Novel Views","created":"2021-05-27","cited_by_count":76,"area":null},{"id":"2212.03239","title":"Perspective Fields for Single Image Camera Calibration","created":"2022-12-06","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":"2103.07074","title":"Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion","created":"2021-03-12","cited_by_count":72,"area":null},{"id":"2203.01452","title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","created":"2022-03-02","cited_by_count":72,"area":null},{"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":"2203.16797","title":"When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning","created":"2022-03-31","cited_by_count":65,"area":null},{"id":"2104.04891","title":"SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds","created":"2021-04-11","cited_by_count":64,"area":null},{"id":"2503.16591","title":"UniK3D: Universal Camera Monocular 3D Estimation","created":"2025-03-20","cited_by_count":62,"area":null},{"id":"2203.00838","title":"OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion","created":"2022-03-02","cited_by_count":61,"area":null},{"id":"2111.15669","title":"360MonoDepth: High-Resolution 360{\\deg} Monocular Depth Estimation","created":"2021-11-30","cited_by_count":60,"area":null},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56,"area":null},{"id":"2203.05272","title":"Contrastive Boundary Learning for Point Cloud Segmentation","created":"2022-03-10","cited_by_count":56,"area":null},{"id":"2310.08586","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","created":"2023-10-12","cited_by_count":56,"area":null},{"id":"2202.08471","title":"TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baseline","created":"2022-02-17","cited_by_count":55,"area":null},{"id":"2112.02990","title":"4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding","created":"2021-12-06","cited_by_count":54,"area":null},{"id":"2203.09065","title":"STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset","created":"2022-03-17","cited_by_count":53,"area":null},{"id":"2303.00246","title":"ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution","created":"2023-03-01","cited_by_count":53,"area":null},{"id":"2409.06704","title":"GeoCalib: Learning Single-image Calibration with Geometric Optimization","created":"2024-09-10","cited_by_count":52,"area":null},{"id":"2107.02389","title":"Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling","created":"2021-07-06","cited_by_count":51,"area":null},{"id":"2201.04494","title":"SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds","created":"2022-01-12","cited_by_count":50,"area":null},{"id":"2104.02243","title":"3D-to-2D Distillation for Indoor Scene Parsing","created":"2021-04-06","cited_by_count":48,"area":null},{"id":"2207.11860","title":"Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation","created":"2022-07-25","cited_by_count":46,"area":null},{"id":"2108.07628","title":"Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation","created":"2021-08-17","cited_by_count":44,"area":null},{"id":"2104.00568","title":"LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering","created":"2021-04-01","cited_by_count":43,"area":null},{"id":"2108.06076","title":"PVT: Point-Voxel Transformer for Point Cloud Learning","created":"2021-08-13","cited_by_count":43,"area":null},{"id":"2111.00207","title":"PatchFormer: An Efficient Point Transformer with Patch Attention","created":"2021-10-30","cited_by_count":43,"area":null},{"id":"2205.05570","title":"Review on Panoramic Imaging and Its Applications in Scene Understanding","created":"2022-05-11","cited_by_count":43,"area":null},{"id":"2304.07803","title":"EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation","created":"2023-04-16","cited_by_count":43,"area":null},{"id":"2208.13241","title":"Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image","created":"2022-08-28","cited_by_count":42,"area":null},{"id":"2106.04180","title":"Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models","created":"2021-06-08","cited_by_count":41,"area":null},{"id":"2210.08064","title":"LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds","created":"2022-10-14","cited_by_count":41,"area":null},{"id":"2211.14462","title":"Meta Architecture for Point Cloud Analysis","created":"2022-11-26","cited_by_count":40,"area":null},{"id":"2112.14440","title":"ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation","created":"2021-12-29","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":"2406.12849","title":"Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation","created":"2024-06-18","cited_by_count":38,"area":null},{"id":"2109.02749","title":"Pano3D: A Holistic Benchmark and a Solid Baseline for $360^o$ Depth Estimation","created":"2021-09-06","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":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36,"area":null},{"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":"2108.11544","title":"Vision-Language Navigation: A Survey and Taxonomy","created":"2021-08-26","cited_by_count":34,"area":null},{"id":"2305.16404","title":"GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds","created":"2023-05-25","cited_by_count":34,"area":null},{"id":"2403.12505","title":"Semantics, Distortion, and Style Matter: Towards Source-free UDA for Panoramic Segmentation","created":"2024-03-19","cited_by_count":34,"area":null},{"id":"2108.10743","title":"DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization","created":"2021-08-24","cited_by_count":33,"area":null},{"id":"2111.12242","title":"PU-Transformer: Point Cloud Upsampling Transformer","created":"2021-11-24","cited_by_count":32,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2105.06461","title":"3D Spatial Recognition without Spatially Labeled 3D","created":"2021-05-13","cited_by_count":31,"area":null},{"id":"2403.16376","title":"Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion","created":"2024-03-25","cited_by_count":31,"area":null},{"id":"2107.03172","title":"Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World","created":"2021-07-07","cited_by_count":30,"area":null},{"id":"2311.17389","title":"360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries","created":"2023-11-29","cited_by_count":30,"area":null},{"id":"2203.01824","title":"LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network","created":"2022-03-03","cited_by_count":29,"area":null},{"id":"2404.16501","title":"360SFUDA++: Towards Source-free UDA for Panoramic Segmentation by Learning Reliable Category Prototypes","created":"2024-04-25","cited_by_count":28,"area":null},{"id":"2410.08208","title":"SPA: 3D Spatial-Awareness Enables Effective Embodied Representation","created":"2024-10-10","cited_by_count":28,"area":null},{"id":"2503.07098","title":"OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation","created":"2025-03-10","cited_by_count":28,"area":null},{"id":"2507.22412","title":"UAVScenes: A Multi-Modal Dataset for UAVs","created":"2025-07-30","cited_by_count":27,"area":null},{"id":"2112.06179","title":"BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learning","created":"2021-12-12","cited_by_count":26,"area":null},{"id":"2202.13388","title":"PanoFlow: Learning 360{\\deg} Optical Flow for Surrounding Temporal Understanding","created":"2022-02-27","cited_by_count":26,"area":null},{"id":"2306.03403","title":"SGAT4PASS: Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentation","created":"2023-06-06","cited_by_count":26,"area":null},{"id":"2401.02416","title":"ODIN: A Single Model for 2D and 3D Segmentation","created":"2024-01-04","cited_by_count":25,"area":null},{"id":"2509.26618","title":"DA$^{2}$: Depth Anything in Any Direction","created":"2025-09-30","cited_by_count":25,"area":null},{"id":"2512.16913","title":"Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation","created":"2025-12-18","cited_by_count":25,"area":null},{"id":"2207.04997","title":"A Closer Look at Invariances in Self-supervised Pre-training for 3D Vision","created":"2022-07-11","cited_by_count":24,"area":null},{"id":"2209.13603","title":"Scalable and Equivariant Spherical CNNs by Discrete-Continuous (DISCO) Convolutions","created":"2022-09-27","cited_by_count":24,"area":null},{"id":"2304.10756","title":"Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation","created":"2023-04-21","cited_by_count":24,"area":null},{"id":"2305.02627","title":"UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building Instance Segmentation","created":"2023-05-04","cited_by_count":24,"area":null},{"id":"2312.11269","title":"Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation","created":"2023-12-18","cited_by_count":24,"area":null},{"id":"2502.10444","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","created":"2025-02-11","cited_by_count":24,"area":null},{"id":"2203.09855","title":"Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion","created":"2022-03-18","cited_by_count":23,"area":null},{"id":"2108.04023","title":"DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation","created":"2021-08-09","cited_by_count":22,"area":null},{"id":"2108.09174","title":"Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance","created":"2021-08-20","cited_by_count":22,"area":null},{"id":"2406.13378","title":"PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation","created":"2024-06-19","cited_by_count":22,"area":null},{"id":"2105.00931","title":"GridToPix: Training Embodied Agents with Minimal Supervision","created":"2021-04-14","cited_by_count":21,"area":null},{"id":"2208.04309","title":"3D Vision with Transformers: A Survey","created":"2022-08-08","cited_by_count":21,"area":null},{"id":"2309.15702","title":"SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction","created":"2023-09-27","cited_by_count":21,"area":null},{"id":"2303.10559","title":"Deep Learning for Camera Calibration and Beyond: A Survey","created":"2023-03-19","cited_by_count":20,"area":null},{"id":"2307.07313","title":"HEAL-SWIN: A Vision Transformer On The Sphere","created":"2023-07-14","cited_by_count":20,"area":null},{"id":"2104.03584","title":"PDO-eS2CNNs: Partial Differential Operator Based Equivariant Spherical CNNs","created":"2021-04-08","cited_by_count":19,"area":null},{"id":"2109.10563","title":"Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning","created":"2021-09-22","cited_by_count":19,"area":null},{"id":"2110.05769","title":"Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2203.08122","title":"From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2206.01738","title":"RIDDLE: Lidar Data Compression with Range Image Deep Delta Encoding","created":"2022-06-02","cited_by_count":19,"area":null}],"next_cursor":"100"}