{"list":"other","total":83,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"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":"2007.11898","title":"ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM","created":"2020-07-23","cited_by_count":878},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"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":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2104.06405","title":"BARF: Bundle-Adjusting Neural Radiance Fields","created":"2021-04-13","cited_by_count":642},{"id":"1803.08669","title":"Pyramid Stereo Matching Network","created":"2018-03-23","cited_by_count":489},{"id":"1607.02565","title":"Direct Sparse Odometry","created":"2016-07-09","cited_by_count":485},{"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":"2405.10314","title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","created":"2024-05-16","cited_by_count":432},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"1703.04309","title":"End-to-End Learning of Geometry and Context for Deep Stereo Regression","created":"2017-03-13","cited_by_count":360},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263},{"id":"1902.10556","title":"Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference","created":"2019-02-27","cited_by_count":254},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250},{"id":"1904.06587","title":"GA-Net: Guided Aggregation Net for End-to-end Stereo Matching","created":"2019-04-13","cited_by_count":244},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228},{"id":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227},{"id":"2211.11082","title":"DynIBaR: Neural Dynamic Image-Based Rendering","created":"2022-11-20","cited_by_count":224},{"id":"2004.15021","title":"Consistent Video Depth Estimation","created":"2020-04-30","cited_by_count":220},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204},{"id":"2108.08291","title":"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement","created":"2021-08-18","cited_by_count":200},{"id":"2210.13445","title":"Monocular Dynamic View Synthesis: A Reality Check","created":"2022-10-24","cited_by_count":200},{"id":"2301.02239","title":"Robust Dynamic Radiance Fields","created":"2023-01-05","cited_by_count":194},{"id":"2305.03027","title":"NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads","created":"2023-05-04","cited_by_count":194},{"id":"2312.07504","title":"COLMAP-Free 3D Gaussian Splatting","created":"2023-12-12","cited_by_count":193},{"id":"2208.04726","title":"Deep Patch Visual Odometry","created":"2022-08-08","cited_by_count":190},{"id":"2012.05901","title":"Robust Consistent Video Depth Estimation","created":"2020-12-10","cited_by_count":188},{"id":"1905.02082","title":"ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals","created":"2019-05-06","cited_by_count":181},{"id":"2405.17421","title":"MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds","created":"2024-05-27","cited_by_count":179},{"id":"1806.04807","title":"BA-Net: Dense Bundle Adjustment Network","created":"2018-06-13","cited_by_count":175},{"id":"2405.14793","title":"SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow","created":"2024-05-23","cited_by_count":174},{"id":"2306.06362","title":"Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception","created":"2023-06-10","cited_by_count":167},{"id":"2305.06356","title":"HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion","created":"2023-05-10","cited_by_count":161},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161},{"id":"1804.00874","title":"CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM","created":"2018-04-03","cited_by_count":152},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148},{"id":"2012.00726","title":"RAFT-3D: Scene Flow using Rigid-Motion Embeddings","created":"2020-12-01","cited_by_count":122},{"id":"1904.11111","title":"Learning the Depths of Moving People by Watching Frozen People","created":"2019-04-25","cited_by_count":120},{"id":"2402.00847","title":"BootsTAP: Bootstrapped Training for Tracking-Any-Point","created":"2024-02-01","cited_by_count":120},{"id":"2305.14059","title":"Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses","created":"2023-05-23","cited_by_count":107},{"id":"2104.14544","title":"AutoFlow: Learning a Better Training Set for Optical Flow","created":"2021-04-29","cited_by_count":102},{"id":"2406.01493","title":"Learning Temporally Consistent Video Depth from Video Diffusion Priors","created":"2024-06-03","cited_by_count":100},{"id":"1912.04302","title":"DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data","created":"2019-12-09","cited_by_count":77},{"id":"1904.11112","title":"Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes","created":"2019-04-25","cited_by_count":73},{"id":"2404.14351","title":"Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer","created":"2024-04-22","cited_by_count":73},{"id":"2407.05921","title":"TAPVid-3D: A Benchmark for Tracking Any Point in 3D","created":"2024-07-08","cited_by_count":72},{"id":"1708.09204","title":"Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching","created":"2017-08-30","cited_by_count":63},{"id":"2312.04560","title":"NeRFiller: Completing Scenes via Generative 3D Inpainting","created":"2023-12-07","cited_by_count":62},{"id":"2108.01166","title":"Consistent Depth of Moving Objects in Video","created":"2021-08-02","cited_by_count":56},{"id":"2308.10902","title":"CamP: Camera Preconditioning for Neural Radiance Fields","created":"2023-08-21","cited_by_count":55},{"id":"2203.10712","title":"Disentangling Architecture and Training for Optical Flow","created":"2022-03-21","cited_by_count":32},{"id":"2209.08430","title":"DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments","created":"2022-09-17","cited_by_count":27},{"id":"2111.09337","title":"Temporally Consistent Online Depth Estimation in Dynamic Scenes","created":"2021-11-17","cited_by_count":26},{"id":"2403.10755","title":"Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching","created":"2024-03-16","cited_by_count":24},{"id":"2211.13755","title":"TemporalStereo: Efficient Spatial-Temporal Stereo Matching Network","created":"2022-11-24","cited_by_count":12},{"id":"2406.06133","title":"ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models","created":"2024-06-10","cited_by_count":12},{"id":"2008.12295","title":"Reducing Drift in Structure From Motion Using Extended Features","created":"2020-08-27","cited_by_count":10},{"id":"1906.03539","title":"Structure from Motion for Panorama-Style Videos","created":"2019-06-08","cited_by_count":5}],"next_cursor":null}