{"list":"other","total":93,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"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":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"2106.10689","title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","created":"2021-06-20","cited_by_count":1712},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2007.11571","title":"Neural Sparse Voxel Fields","created":"2020-07-22","cited_by_count":959},{"id":"2103.10504","title":"UNETR: Transformers for 3D Medical Image Segmentation","created":"2021-03-18","cited_by_count":959},{"id":"2011.12100","title":"GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields","created":"2020-11-24","cited_by_count":785},{"id":"2003.04618","title":"Convolutional Occupancy Networks","created":"2020-03-10","cited_by_count":761},{"id":"2103.15595","title":"MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo","created":"2021-03-29","cited_by_count":740},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"2202.05263","title":"Block-NeRF: Scalable Large Scene Neural View Synthesis","created":"2022-02-10","cited_by_count":724},{"id":"1912.07372","title":"Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision","created":"2019-12-16","cited_by_count":700},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"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},{"id":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2111.11426","title":"Neural Fields in Visual Computing and Beyond","created":"2021-11-22","cited_by_count":540},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2303.12789","title":"Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions","created":"2023-03-22","cited_by_count":484},{"id":"2103.12352","title":"iMAP: Implicit Mapping and Positioning in Real-Time","created":"2021-03-23","cited_by_count":476},{"id":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459},{"id":"2101.10994","title":"Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes","created":"2021-01-26","cited_by_count":426},{"id":"2111.14791","title":"Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis","created":"2021-11-29","cited_by_count":422},{"id":"2103.15875","title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","created":"2021-03-29","cited_by_count":415},{"id":"2312.00732","title":"Gaussian Grouping: Segment and Edit Anything in 3D Scenes","created":"2023-12-01","cited_by_count":393},{"id":"2012.05877","title":"INeRF: Inverting Neural Radiance Fields for Pose Estimation","created":"2020-12-10","cited_by_count":382},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2112.05139","title":"CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields","created":"2021-12-09","cited_by_count":370},{"id":"2312.02981","title":"ReconFusion: 3D Reconstruction with Diffusion Priors","created":"2023-12-05","cited_by_count":318},{"id":"2112.03288","title":"Dense Depth Priors for Neural Radiance Fields from Sparse Input Views","created":"2021-12-06","cited_by_count":302},{"id":"2011.10379","title":"Neural Scene Graphs for Dynamic Scenes","created":"2020-11-20","cited_by_count":298},{"id":"2205.14401","title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","created":"2022-05-28","cited_by_count":264},{"id":"2109.02497","title":"Voxel Transformer for 3D Object Detection","created":"2021-09-06","cited_by_count":247},{"id":"2205.04334","title":"Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation","created":"2022-05-09","cited_by_count":243},{"id":"2109.01847","title":"Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering","created":"2021-09-04","cited_by_count":228},{"id":"1908.01210","title":"Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer","created":"2019-08-03","cited_by_count":221},{"id":"2302.14859","title":"BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis","created":"2023-02-28","cited_by_count":221},{"id":"2101.02691","title":"Self-Supervised Pretraining of 3D Features on any Point-Cloud","created":"2021-01-07","cited_by_count":217},{"id":"1905.07259","title":"Texture Fields: Learning Texture Representations in Function Space","created":"2019-05-17","cited_by_count":210},{"id":"2012.09165","title":"Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts","created":"2020-12-16","cited_by_count":210},{"id":"2112.05124","title":"Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation","created":"2021-12-09","cited_by_count":209},{"id":"2010.04595","title":"GRF: Learning a General Radiance Field for 3D Representation and Rendering","created":"2020-10-09","cited_by_count":183},{"id":"2212.09802","title":"Panoptic Lifting for 3D Scene Understanding with Neural Fields","created":"2022-12-19","cited_by_count":174},{"id":"2210.10716","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","created":"2022-10-19","cited_by_count":160},{"id":"2106.01178","title":"ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection","created":"2021-06-02","cited_by_count":157},{"id":"2203.11183","title":"Masked Discrimination for Self-Supervised Learning on Point Clouds","created":"2022-03-21","cited_by_count":155},{"id":"2212.06785","title":"Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders","created":"2022-12-13","cited_by_count":144},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130},{"id":"2105.04553","title":"Self-Supervised Learning with Swin Transformers","created":"2021-05-10","cited_by_count":122},{"id":"2304.06906","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","created":"2023-04-14","cited_by_count":113},{"id":"2006.03997","title":"MeshSDF: Differentiable Iso-Surface Extraction","created":"2020-06-06","cited_by_count":112},{"id":"2201.10326","title":"ShapeFormer: Transformer-based Shape Completion via Sparse Representation","created":"2022-01-25","cited_by_count":106},{"id":"2203.10314","title":"Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds","created":"2022-03-19","cited_by_count":102},{"id":"2308.16891","title":"GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields","created":"2023-08-31","cited_by_count":99},{"id":"2112.00322","title":"FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection","created":"2021-12-01","cited_by_count":97},{"id":"2103.06422","title":"Holistic 3D Scene Understanding from a Single Image with Implicit Representation","created":"2021-03-11","cited_by_count":94},{"id":"2203.01913","title":"NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields","created":"2022-03-03","cited_by_count":86},{"id":"2101.01602","title":"STaR: Self-supervised Tracking and Reconstruction of Rigid Objects in Motion with Neural Rendering","created":"2020-12-22","cited_by_count":76},{"id":"2207.13691","title":"ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization","created":"2022-07-27","cited_by_count":72},{"id":"2203.01929","title":"CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation","created":"2022-03-03","cited_by_count":70},{"id":"2303.11327","title":"3D Concept Learning and Reasoning from Multi-View Images","created":"2023-03-20","cited_by_count":60},{"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},{"id":"2303.08129","title":"PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection","created":"2023-03-14","cited_by_count":53},{"id":"2308.12967","title":"NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes","created":"2023-08-24","cited_by_count":53},{"id":"2307.14620","title":"NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection","created":"2023-07-27","cited_by_count":51},{"id":"2301.00157","title":"Ponder: Point Cloud Pre-training via Neural Rendering","created":"2022-12-31","cited_by_count":50},{"id":"2201.00785","title":"Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning","created":"2022-01-03","cited_by_count":46},{"id":"2211.11646","title":"NeRF-RPN: A general framework for object detection in NeRFs","created":"2022-11-21","cited_by_count":46},{"id":"2304.04395","title":"Instance Neural Radiance Field","created":"2023-04-10","cited_by_count":40},{"id":"2207.10228","title":"MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis","created":"2022-07-20","cited_by_count":31},{"id":"2208.11537","title":"PeRFception: Perception using Radiance Fields","created":"2022-08-24","cited_by_count":19},{"id":"2310.12974","title":"FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objects","created":"2023-10-19","cited_by_count":19},{"id":"2305.05026","title":"Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understanding","created":"2023-05-08","cited_by_count":13},{"id":"2402.11141","title":"Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review","created":"2024-02-17","cited_by_count":9}],"next_cursor":null}