{"total":1106,"rows":[{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850,"area":null},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764,"area":null},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712,"area":null},{"id":"2312.10035","title":"Point Transformer V3: Simpler, Faster, Stronger","created":"2023-12-15","cited_by_count":589,"area":null},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559,"area":null},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409,"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":"2205.15585","title":"Decomposing NeRF for Editing via Feature Field Distillation","created":"2022-05-31","cited_by_count":371,"area":null},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327,"area":null},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303,"area":null},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289,"area":null},{"id":"2204.07761","title":"Language-Grounded Indoor 3D Semantic Segmentation in the Wild","created":"2022-04-16","cited_by_count":246,"area":null},{"id":"2102.00463","title":"PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection","created":"2021-01-31","cited_by_count":232,"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":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215,"area":null},{"id":"2103.14635","title":"PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds","created":"2021-03-26","cited_by_count":211,"area":null},{"id":"2203.01509","title":"SoftGroup for 3D Instance Segmentation on Point Clouds","created":"2022-03-03","cited_by_count":200,"area":null},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197,"area":null},{"id":"2403.17846","title":"Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation","created":"2024-03-26","cited_by_count":196,"area":null},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184,"area":null},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181,"area":null},{"id":"2109.00179","title":"Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds","created":"2021-09-01","cited_by_count":180,"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":"2211.16312","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","created":"2022-11-29","cited_by_count":177,"area":null},{"id":"2103.12978","title":"RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation","created":"2021-03-24","cited_by_count":173,"area":null},{"id":"2203.14508","title":"Stratified Transformer for 3D Point Cloud Segmentation","created":"2022-03-28","cited_by_count":167,"area":null},{"id":"2111.03043","title":"A System for General In-Hand Object Re-Orientation","created":"2021-11-04","cited_by_count":165,"area":null},{"id":"2102.04530","title":"(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network","created":"2021-02-08","cited_by_count":164,"area":null},{"id":"2110.14076","title":"CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration","created":"2021-10-26","cited_by_count":152,"area":null},{"id":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147,"area":null},{"id":"2309.05251","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","created":"2023-09-11","cited_by_count":146,"area":null},{"id":"2103.05465","title":"PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency","created":"2021-03-09","cited_by_count":142,"area":null},{"id":"2204.12463","title":"Focal Sparse Convolutional Networks for 3D Object Detection","created":"2022-04-26","cited_by_count":142,"area":null},{"id":"2103.01128","title":"InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring","created":"2021-03-01","cited_by_count":141,"area":null},{"id":"2306.17817","title":"Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation","created":"2023-06-30","cited_by_count":138,"area":null},{"id":"2303.17597","title":"Robo3D: Towards Robust and Reliable 3D Perception against Corruptions","created":"2023-03-30","cited_by_count":129,"area":null},{"id":"2110.02210","title":"Mix3D: Out-of-Context Data Augmentation for 3D Scenes","created":"2021-10-05","cited_by_count":126,"area":null},{"id":"2203.16258","title":"Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data","created":"2022-03-30","cited_by_count":126,"area":null},{"id":"2303.12766","title":"Spherical Transformer for LiDAR-based 3D Recognition","created":"2023-03-22","cited_by_count":125,"area":null},{"id":"2306.09347","title":"Segment Any Point Cloud Sequences by Distilling Vision Foundation Models","created":"2023-06-15","cited_by_count":125,"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":"2209.05324","title":"Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe","created":"2022-09-12","cited_by_count":122,"area":null},{"id":"2301.06051","title":"DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets","created":"2023-01-15","cited_by_count":122,"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":"2305.11487","title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","created":"2023-05-19","cited_by_count":115,"area":null},{"id":"2304.06906","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","created":"2023-04-14","cited_by_count":113,"area":null},{"id":"2206.00878","title":"EfficientNeRF: Efficient Neural Radiance Fields","created":"2022-06-02","cited_by_count":111,"area":null},{"id":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","cited_by_count":110,"area":null},{"id":"2305.03045","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","created":"2023-05-04","cited_by_count":109,"area":null},{"id":"2112.04702","title":"Fast Point Transformer","created":"2021-12-09","cited_by_count":104,"area":null},{"id":"2405.20853","title":"MeshXL: Neural Coordinate Field for Generative 3D Foundation Models","created":"2024-05-31","cited_by_count":103,"area":null},{"id":"2211.11744","title":"Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes","created":"2022-11-21","cited_by_count":101,"area":null},{"id":"2108.07478","title":"Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks","created":"2021-08-17","cited_by_count":99,"area":null},{"id":"2112.00322","title":"FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection","created":"2021-12-01","cited_by_count":97,"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":"2311.14405","title":"OneFormer3D: One Transformer for Unified Point Cloud Segmentation","created":"2023-11-24","cited_by_count":95,"area":null},{"id":"2301.03580","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","created":"2023-01-09","cited_by_count":94,"area":null},{"id":"2304.00962","title":"RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding","created":"2023-04-03","cited_by_count":94,"area":null},{"id":"2201.01831","title":"POCO: Point Convolution for Surface Reconstruction","created":"2022-01-05","cited_by_count":92,"area":null},{"id":"2312.11557","title":"SAI3D: Segment Any Instance in 3D Scenes","created":"2023-12-17","cited_by_count":90,"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":"2303.04748","title":"CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP","created":"2023-03-08","cited_by_count":89,"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":"2207.08560","title":"Latency-Aware Collaborative Perception","created":"2022-07-18","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":"2111.12591","title":"Lepard: Learning partial point cloud matching in rigid and deformable scenes","created":"2021-11-24","cited_by_count":85,"area":null},{"id":"2205.05740","title":"Surface Representation for Point Clouds","created":"2022-05-11","cited_by_count":84,"area":null},{"id":"2403.15624","title":"Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting","created":"2024-03-22","cited_by_count":82,"area":null},{"id":"2405.02771","title":"MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning","created":"2024-05-04","cited_by_count":77,"area":null},{"id":"2102.08009","title":"EfficientLPS: Efficient LiDAR Panoptic Segmentation","created":"2021-02-16","cited_by_count":76,"area":null},{"id":"2107.05399","title":"Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation","created":"2021-07-12","cited_by_count":76,"area":null},{"id":"2204.12667","title":"MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation","created":"2022-04-27","cited_by_count":76,"area":null},{"id":"2103.07466","title":"3D Semantic Scene Completion: a Survey","created":"2021-03-12","cited_by_count":74,"area":null},{"id":"2208.00223","title":"PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds","created":"2022-07-30","cited_by_count":74,"area":null},{"id":"2209.09385","title":"LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception","created":"2022-09-19","cited_by_count":74,"area":null},{"id":"2308.07732","title":"UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation","created":"2023-08-15","cited_by_count":74,"area":null},{"id":"2204.10319","title":"TorchSparse: Efficient Point Cloud Inference Engine","created":"2022-04-21","cited_by_count":73,"area":null},{"id":"2301.08739","title":"FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer","created":"2023-01-20","cited_by_count":73,"area":null},{"id":"2310.08370","title":"UniPAD: A Universal Pre-training Paradigm for Autonomous Driving","created":"2023-10-12","cited_by_count":73,"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":"2206.10555","title":"LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs","created":"2022-06-21","cited_by_count":72,"area":null},{"id":"2111.11187","title":"PointMixer: MLP-Mixer for Point Cloud Understanding","created":"2021-11-22","cited_by_count":71,"area":null},{"id":"2205.02825","title":"Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations","created":"2022-05-05","cited_by_count":71,"area":null},{"id":"2111.10633","title":"Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression","created":"2021-11-20","cited_by_count":70,"area":null},{"id":"2405.11442","title":"Unifying 3D Vision-Language Understanding via Promptable Queries","created":"2024-05-19","cited_by_count":70,"area":null},{"id":"2203.08537","title":"Scribble-Supervised LiDAR Semantic Segmentation","created":"2022-03-16","cited_by_count":69,"area":null},{"id":"2212.00836","title":"UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding","created":"2022-12-01","cited_by_count":69,"area":null},{"id":"2303.08231","title":"Rotation-Invariant Transformer for Point Cloud Matching","created":"2023-03-14","cited_by_count":69,"area":null},{"id":"2205.13713","title":"PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences","created":"2022-05-27","cited_by_count":68,"area":null},{"id":"2212.05867","title":"ALSO: Automotive Lidar Self-supervision by Occupancy estimation","created":"2022-12-12","cited_by_count":68,"area":null},{"id":"2303.08600","title":"MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving","created":"2023-03-15","cited_by_count":68,"area":null},{"id":"2103.12266","title":"Deep Implicit Moving Least-Squares Functions for 3D Reconstruction","created":"2021-03-23","cited_by_count":67,"area":null},{"id":"2102.12472","title":"4D Panoptic LiDAR Segmentation","created":"2021-02-24","cited_by_count":65,"area":null},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","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":"2311.15383","title":"Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding","created":"2023-11-26","cited_by_count":64,"area":null},{"id":"2312.17118","title":"Fully Sparse 3D Occupancy Prediction","created":"2023-12-28","cited_by_count":64,"area":null},{"id":"2312.17232","title":"Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels","created":"2023-12-28","cited_by_count":64,"area":null},{"id":"2104.11225","title":"Pri3D: Can 3D Priors Help 2D Representation Learning?","created":"2021-04-22","cited_by_count":61,"area":null},{"id":"2102.08945","title":"Weakly Supervised Learning of Rigid 3D Scene Flow","created":"2021-02-17","cited_by_count":60,"area":null}],"next_cursor":"100"}