{"list":"other","total":91,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"2112.07945","title":"Efficient Geometry-aware 3D Generative Adversarial Networks","created":"2021-12-15","cited_by_count":1205},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"1906.01618","title":"Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations","created":"2019-06-04","cited_by_count":864},{"id":"1610.06475","title":"ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras","created":"2016-10-20","cited_by_count":806},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"1912.07372","title":"Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision","created":"2019-12-16","cited_by_count":700},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2104.06405","title":"BARF: Bundle-Adjusting Neural Radiance Fields","created":"2021-04-13","cited_by_count":642},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590},{"id":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"id":"1912.06378","title":"Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching","created":"2019-12-13","cited_by_count":417},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"1912.08804","title":"SynSin: End-to-end View Synthesis from a Single Image","created":"2019-12-18","cited_by_count":364},{"id":"2312.13150","title":"Splatter Image: Ultra-Fast Single-View 3D Reconstruction","created":"2023-12-20","cited_by_count":364},{"id":"1603.09114","title":"LIFT: Learned Invariant Feature Transform","created":"2016-03-30","cited_by_count":306},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277},{"id":"1704.05939","title":"HPatches: A benchmark and evaluation of handcrafted and learned local descriptors","created":"2017-04-19","cited_by_count":264},{"id":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"2108.13826","title":"Self-Calibrating Neural Radiance Fields","created":"2021-08-31","cited_by_count":204},{"id":"1612.02401","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","created":"2016-12-07","cited_by_count":201},{"id":"2108.08291","title":"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement","created":"2021-08-18","cited_by_count":200},{"id":"1812.04605","title":"DeepV2D: Video to Depth with Differentiable Structure from Motion","created":"2018-12-11","cited_by_count":185},{"id":"2109.01750","title":"CodeNeRF: Disentangled Neural Radiance Fields for Object Categories","created":"2021-09-03","cited_by_count":183},{"id":"2408.13912","title":"Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs","created":"2024-08-25","cited_by_count":178},{"id":"2208.14201","title":"ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer","created":"2022-08-30","cited_by_count":171},{"id":"2211.10408","title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","created":"2022-11-18","cited_by_count":166},{"id":"2409.19152","title":"MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion","created":"2024-09-27","cited_by_count":162},{"id":"1709.07492","title":"Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image","created":"2017-09-21","cited_by_count":161},{"id":"2306.09310","title":"Infinite Photorealistic Worlds using Procedural Generation","created":"2023-06-15","cited_by_count":147},{"id":"2306.15667","title":"PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment","created":"2023-06-27","cited_by_count":147},{"id":"2103.00783","title":"PENet: Towards Precise and Efficient Image Guided Depth Completion","created":"2021-03-01","cited_by_count":146},{"id":"1807.00275","title":"Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera","created":"2018-07-01","cited_by_count":140},{"id":"2402.14817","title":"Cameras as Rays: Pose Estimation via Ray Diffusion","created":"2024-02-22","cited_by_count":131},{"id":"1812.00488","title":"DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image","created":"2018-12-02","cited_by_count":129},{"id":"2201.02767","title":"QuadTree Attention for Vision Transformers","created":"2022-01-08","cited_by_count":129},{"id":"1904.00889","title":"Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters","created":"2019-04-01","cited_by_count":118},{"id":"2406.04343","title":"Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image","created":"2024-06-06","cited_by_count":116},{"id":"1908.01238","title":"Learning Guided Convolutional Network for Depth Completion","created":"2019-08-03","cited_by_count":111},{"id":"1803.09326","title":"Deep Depth Completion of a Single RGB-D Image","created":"2018-03-25","cited_by_count":110},{"id":"1808.00150","title":"Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network","created":"2018-08-01","cited_by_count":110},{"id":"2207.05736","title":"Vision Transformer for NeRF-Based View Synthesis from a Single Input Image","created":"2022-07-12","cited_by_count":104},{"id":"2208.05963","title":"RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild","created":"2022-08-11","cited_by_count":102},{"id":"2008.07928","title":"Visibility-aware Multi-view Stereo Network","created":"2020-08-18","cited_by_count":98},{"id":"1808.01900","title":"DeepTAM: Deep Tracking and Mapping","created":"2018-08-06","cited_by_count":87},{"id":"2305.04926","title":"RelPose++: Recovering 6D Poses from Sparse-view Observations","created":"2023-05-08","cited_by_count":87},{"id":"2204.05735","title":"GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimation","created":"2022-04-12","cited_by_count":86},{"id":"2201.01501","title":"Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation","created":"2022-01-05","cited_by_count":82},{"id":"1902.05356","title":"Sparse and noisy LiDAR completion with RGB guidance and uncertainty","created":"2019-02-14","cited_by_count":79},{"id":"2103.16317","title":"Deep Regression on Manifolds: A 3D Rotation Case Study","created":"2021-03-30","cited_by_count":67},{"id":"2303.14478","title":"DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields","created":"2023-03-25","cited_by_count":60},{"id":"2403.11270","title":"Bilateral Propagation Network for Depth Completion","created":"2024-03-17","cited_by_count":60},{"id":"2308.10902","title":"CamP: Camera Preconditioning for Neural Radiance Fields","created":"2023-08-21","cited_by_count":55},{"id":"2205.04502","title":"Multiview Stereo with Cascaded Epipolar RAFT","created":"2022-05-09","cited_by_count":51},{"id":"2401.11673","title":"MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo","created":"2024-01-22","cited_by_count":50},{"id":"2310.08956","title":"LRRU: Long-short Range Recurrent Updating Networks for Depth Completion","created":"2023-10-13","cited_by_count":49},{"id":"2104.13325","title":"MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions","created":"2021-04-27","cited_by_count":43},{"id":"2208.13241","title":"Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image","created":"2022-08-28","cited_by_count":42},{"id":"2403.15008","title":"Tri-Perspective View Decomposition for Geometry-Aware Depth Completion","created":"2024-03-22","cited_by_count":42},{"id":"2006.02708","title":"Auto-Rectify Network for Unsupervised Indoor Depth Estimation","created":"2020-06-04","cited_by_count":39},{"id":"2209.06681","title":"A Benchmark and a Baseline for Robust Multi-view Depth Estimation","created":"2022-09-13","cited_by_count":39},{"id":"2208.08988","title":"The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs","created":"2022-08-18","cited_by_count":38},{"id":"2306.10988","title":"Tame a Wild Camera: In-the-Wild Monocular Camera Calibration","created":"2023-06-19","cited_by_count":34},{"id":"2302.06833","title":"VQ3D: Learning a 3D-Aware Generative Model on ImageNet","created":"2023-02-14","cited_by_count":32},{"id":"2001.02643","title":"CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus","created":"2020-01-08","cited_by_count":30},{"id":"1608.05684","title":"Detecting Vanishing Points using Global Image Context in a Non-Manhattan World","created":"2016-08-19","cited_by_count":27},{"id":"2204.13635","title":"SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion","created":"2022-04-28","cited_by_count":23},{"id":"2312.08568","title":"NViST: In the Wild New View Synthesis from a Single Image with Transformers","created":"2023-12-13","cited_by_count":19},{"id":"2310.00632","title":"Win-Win: Training High-Resolution Vision Transformers from Two Windows","created":"2023-10-01","cited_by_count":12},{"id":"2309.00655","title":"RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion","created":"2023-09-01","cited_by_count":11},{"id":"2308.15984","title":"Learning Structure-from-Motion with Graph Attention Networks","created":"2023-08-30","cited_by_count":10},{"id":"2307.15381","title":"AffineGlue: Joint Matching and Robust Estimation","created":"2023-07-28","cited_by_count":5}],"next_cursor":null}