{"total":223,"rows":[{"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":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381,"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":"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":"2403.14166","title":"Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians","created":"2024-03-21","cited_by_count":213,"area":null},{"id":"2206.00630","title":"Unifying Voxel-based Representation with Transformer for 3D Object Detection","created":"2022-06-01","cited_by_count":202,"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":"2112.06375","title":"Embracing Single Stride 3D Object Detector with Sparse Transformer","created":"2021-12-13","cited_by_count":193,"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":"2203.14508","title":"Stratified Transformer for 3D Point Cloud Segmentation","created":"2022-03-28","cited_by_count":167,"area":null},{"id":"2101.06742","title":"Deep Parametric Continuous Convolutional Neural Networks","created":"2021-01-17","cited_by_count":161,"area":null},{"id":"2211.05272","title":"GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts","created":"2022-11-10","cited_by_count":139,"area":null},{"id":"2203.11139","title":"Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds","created":"2022-03-21","cited_by_count":131,"area":null},{"id":"2303.12766","title":"Spherical Transformer for LiDAR-based 3D Recognition","created":"2023-03-22","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":"2106.13365","title":"RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection","created":"2021-06-25","cited_by_count":115,"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":"2303.01237","title":"FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation","created":"2023-03-02","cited_by_count":114,"area":null},{"id":"2205.03892","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders","created":"2022-05-08","cited_by_count":105,"area":null},{"id":"2305.19590","title":"Neural Kernel Surface Reconstruction","created":"2023-05-31","cited_by_count":104,"area":null},{"id":"2205.07403","title":"PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection","created":"2022-05-16","cited_by_count":99,"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":"2210.07372","title":"SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds","created":"2022-10-13","cited_by_count":92,"area":null},{"id":"2112.09205","title":"AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds","created":"2021-12-16","cited_by_count":88,"area":null},{"id":"2205.05740","title":"Surface Representation for Point Clouds","created":"2022-05-11","cited_by_count":84,"area":null},{"id":"2108.08617","title":"Spatially-Adaptive Image Restoration using Distortion-Guided Networks","created":"2021-08-19","cited_by_count":77,"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":"2209.09385","title":"LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception","created":"2022-09-19","cited_by_count":74,"area":null},{"id":"2111.11187","title":"PointMixer: MLP-Mixer for Point Cloud Understanding","created":"2021-11-22","cited_by_count":71,"area":null},{"id":"2103.09136","title":"QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection","created":"2021-03-16","cited_by_count":70,"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":"2209.03102","title":"MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection","created":"2022-09-07","cited_by_count":62,"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":"2210.04264","title":"CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds","created":"2022-10-09","cited_by_count":58,"area":null},{"id":"2203.05272","title":"Contrastive Boundary Learning for Point Cloud Segmentation","created":"2022-03-10","cited_by_count":56,"area":null},{"id":"2207.09778","title":"CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation","created":"2022-07-20","cited_by_count":54,"area":null},{"id":"2109.09163","title":"CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulation","created":"2021-09-19","cited_by_count":49,"area":null},{"id":"2307.10784","title":"SMURF: Spatial Multi-Representation Fusion for 3D Object Detection with 4D Imaging Radar","created":"2023-07-20","cited_by_count":49,"area":null},{"id":"2203.09704","title":"VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention","created":"2022-03-18","cited_by_count":48,"area":null},{"id":"2301.01100","title":"Understanding Imbalanced Semantic Segmentation Through Neural Collapse","created":"2023-01-03","cited_by_count":46,"area":null},{"id":"2109.11615","title":"Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving","created":"2021-09-23","cited_by_count":45,"area":null},{"id":"2310.20234","title":"HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds","created":"2023-10-31","cited_by_count":45,"area":null},{"id":"2303.16958","title":"PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations","created":"2023-03-29","cited_by_count":42,"area":null},{"id":"2103.09666","title":"Multimodal End-to-End Sparse Model for Emotion Recognition","created":"2021-03-17","cited_by_count":40,"area":null},{"id":"2106.13381","title":"To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels","created":"2021-06-25","cited_by_count":39,"area":null},{"id":"2302.02367","title":"FastPillars: A Deployment-friendly Pillar-based 3D Detector","created":"2023-02-05","cited_by_count":39,"area":null},{"id":"2308.00353","title":"Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding","created":"2023-08-01","cited_by_count":38,"area":null},{"id":"2207.09763","title":"GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation","created":"2022-07-20","cited_by_count":35,"area":null},{"id":"2208.00281","title":"Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding","created":"2022-07-30","cited_by_count":35,"area":null},{"id":"2412.04459","title":"Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering","created":"2024-12-05","cited_by_count":35,"area":null},{"id":"2303.11203","title":"Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation","created":"2023-03-20","cited_by_count":33,"area":null},{"id":"2406.12095","title":"DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features","created":"2024-06-17","cited_by_count":33,"area":null},{"id":"2210.07442","title":"Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds","created":"2022-10-14","cited_by_count":32,"area":null},{"id":"2308.16139","title":"MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Vision","created":"2023-08-30","cited_by_count":32,"area":null},{"id":"2210.09267","title":"CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection","created":"2022-10-17","cited_by_count":30,"area":null},{"id":"2205.15156","title":"Towards Efficient 3D Object Detection with Knowledge Distillation","created":"2022-05-30","cited_by_count":29,"area":"distill"},{"id":"2209.14201","title":"Spatial Pruned Sparse Convolution for Efficient 3D Object Detection","created":"2022-09-28","cited_by_count":26,"area":null},{"id":"2305.14335","title":"Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentation","created":"2023-05-23","cited_by_count":26,"area":null},{"id":"2207.01580","title":"Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks","created":"2022-07-04","cited_by_count":24,"area":null},{"id":"2212.03273","title":"Giga-SSL: Self-Supervised Learning for Gigapixel Images","created":"2022-12-06","cited_by_count":24,"area":null},{"id":"2407.07995","title":"Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation","created":"2024-07-10","cited_by_count":23,"area":null},{"id":"2212.07289","title":"ConQueR: Query Contrast Voxel-DETR for 3D Object Detection","created":"2022-12-14","cited_by_count":21,"area":null},{"id":"2303.11610","title":"Novel Class Discovery for 3D Point Cloud Semantic Segmentation","created":"2023-03-21","cited_by_count":21,"area":null},{"id":"2104.13316","title":"Building-GAN: Graph-Conditioned Architectural Volumetric Design Generation","created":"2021-04-27","cited_by_count":20,"area":null},{"id":"2203.16832","title":"Point Scene Understanding via Disentangled Instance Mesh Reconstruction","created":"2022-03-31","cited_by_count":20,"area":null},{"id":"2308.14619","title":"Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation","created":"2023-08-28","cited_by_count":20,"area":null},{"id":"2207.09332","title":"Rethinking IoU-based Optimization for Single-stage 3D Object Detection","created":"2022-07-19","cited_by_count":19,"area":null},{"id":"2307.09316","title":"MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds","created":"2023-07-18","cited_by_count":19,"area":null},{"id":"2103.01548","title":"PFA: Privacy-preserving Federated Adaptation for Effective Model Personalization","created":"2021-03-02","cited_by_count":18,"area":null},{"id":"2104.00749","title":"Anytime Dense Prediction with Confidence Adaptivity","created":"2021-04-01","cited_by_count":18,"area":null},{"id":"2301.00970","title":"Benchmarking the Robustness of LiDAR Semantic Segmentation Models","created":"2023-01-03","cited_by_count":18,"area":null},{"id":"2103.04056","title":"A Simple and Efficient Multi-task Network for 3D Object Detection and Road Understanding","created":"2021-03-06","cited_by_count":17,"area":null},{"id":"2208.09801","title":"PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition","created":"2022-08-21","cited_by_count":16,"area":null},{"id":"2308.06534","title":"Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical Imaging","created":"2023-08-12","cited_by_count":16,"area":null},{"id":"2102.12093","title":"PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features","created":"2021-02-24","cited_by_count":15,"area":null},{"id":"2111.11704","title":"Deep Point Cloud Reconstruction","created":"2021-11-23","cited_by_count":15,"area":null},{"id":"2407.16424","title":"ESOD: Efficient Small Object Detection on High-Resolution Images","created":"2024-07-23","cited_by_count":15,"area":null},{"id":"2202.10047","title":"PCSCNet: Fast 3D Semantic Segmentation of LiDAR Point Cloud for Autonomous Car using Point Convolution and Sparse Convolution Network","created":"2022-02-21","cited_by_count":14,"area":null},{"id":"2206.08194","title":"Online Segmentation of LiDAR Sequences: Dataset and Algorithm","created":"2022-06-16","cited_by_count":14,"area":null},{"id":"2211.13067","title":"Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection","created":"2022-11-23","cited_by_count":14,"area":null},{"id":"2401.02702","title":"VoxelNextFusion: A Simple, Unified and Effective Voxel Fusion Framework for Multi-Modal 3D Object Detection","created":"2024-01-05","cited_by_count":14,"area":null},{"id":"2106.14087","title":"Radar Voxel Fusion for 3D Object Detection","created":"2021-06-26","cited_by_count":13,"area":null},{"id":"2204.01599","title":"DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation","created":"2022-04-04","cited_by_count":13,"area":null},{"id":"2305.15832","title":"All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation","created":"2023-05-25","cited_by_count":13,"area":null},{"id":"2407.11569","title":"SFPNet: Sparse Focal Point Network for Semantic Segmentation on General LiDAR Point Clouds","created":"2024-07-16","cited_by_count":13,"area":null},{"id":"2501.17821","title":"SSF: Sparse Long-Range Scene Flow for Autonomous Driving","created":"2025-01-29","cited_by_count":13,"area":null},{"id":"2208.11658","title":"AGO-Net: Association-Guided 3D Point Cloud Object Detection Network","created":"2022-08-24","cited_by_count":12,"area":null},{"id":"2303.16482","title":"Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields","created":"2023-03-29","cited_by_count":12,"area":null},{"id":"2407.11564","title":"SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation","created":"2024-07-16","cited_by_count":12,"area":null},{"id":"2408.05815","title":"HySparK: Hybrid Sparse Masking for Large Scale Medical Image Pre-Training","created":"2024-08-11","cited_by_count":12,"area":null},{"id":"2106.06882","title":"Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems","created":"2021-06-12","cited_by_count":11,"area":null},{"id":"2206.10118","title":"HOPE: Hierarchical Spatial-temporal Network for Occupancy Flow Prediction","created":"2022-06-21","cited_by_count":11,"area":null},{"id":"2412.07360","title":"Efficient 3D Recognition with Event-driven Spike Sparse Convolution","created":"2024-12-10","cited_by_count":11,"area":null},{"id":"2105.02726","title":"SparseConvMIL: Sparse Convolutional Context-Aware Multiple Instance Learning for Whole Slide Image Classification","created":"2021-05-06","cited_by_count":10,"area":null},{"id":"2107.00400","title":"Lossless Coding of Point Cloud Geometry using a Deep Generative Model","created":"2021-07-01","cited_by_count":10,"area":null},{"id":"2404.03836","title":"PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model","created":"2024-04-04","cited_by_count":9,"area":"mllm"},{"id":"2210.15904","title":"Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud Analysis","created":"2022-10-28","cited_by_count":8,"area":null}],"next_cursor":"100"}