{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"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":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"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":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"2304.06706","title":"Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields","created":"2023-04-13","cited_by_count":671},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"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":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"2403.12013","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image","created":"2024-03-18","cited_by_count":286},{"id":"2105.01859","title":"Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors","created":"2021-05-05","cited_by_count":246},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"2303.06615","title":"Iterative Geometry Encoding Volume for Stereo Matching","created":"2023-03-12","cited_by_count":190},{"id":"2307.14460","title":"MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation","created":"2023-07-26","cited_by_count":174},{"id":"2204.00987","title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","created":"2022-04-03","cited_by_count":168},{"id":"2409.18124","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction","created":"2024-09-26","cited_by_count":166},{"id":"2206.08367","title":"SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation","created":"2022-06-16","cited_by_count":146},{"id":"1810.02695","title":"Learning Depth with Convolutional Spatial Propagation Network","created":"2018-10-04","cited_by_count":136},{"id":"2203.02146","title":"Attention Concatenation Volume for Accurate and Efficient Stereo Matching","created":"2022-03-04","cited_by_count":130},{"id":"1908.01238","title":"Learning Guided Convolutional Network for Depth Completion","created":"2019-08-03","cited_by_count":111},{"id":"1911.05377","title":"CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion","created":"2019-11-13","cited_by_count":110},{"id":"2306.17253","title":"Towards Zero-Shot Scale-Aware Monocular Depth Estimation","created":"2023-06-29","cited_by_count":101},{"id":"2203.15132","title":"LocalBins: Improving Depth Estimation by Learning Local Distributions","created":"2022-03-28","cited_by_count":94},{"id":"2304.13030","title":"CompletionFormer: Depth Completion with Convolutions and Vision Transformers","created":"2023-04-25","cited_by_count":93},{"id":"1904.11112","title":"Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes","created":"2019-04-25","cited_by_count":73},{"id":"2202.09769","title":"Dynamic Spatial Propagation Network for Depth Completion","created":"2022-02-20","cited_by_count":71},{"id":"2403.11270","title":"Bilateral Propagation Network for Depth Completion","created":"2024-03-17","cited_by_count":60},{"id":"2209.12699","title":"Accurate and Efficient Stereo Matching via Attention Concatenation Volume","created":"2022-09-23","cited_by_count":59},{"id":"2409.00638","title":"IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching","created":"2024-09-01","cited_by_count":59},{"id":"2410.03645","title":"GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs","created":"2024-10-04","cited_by_count":52},{"id":"2110.11590","title":"DIML/CVL RGB-D Dataset: 2M RGB-D Images of Natural Indoor and Outdoor Scenes","created":"2021-10-22","cited_by_count":46},{"id":"2312.02284","title":"PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation","created":"2023-12-04","cited_by_count":41},{"id":"2209.13362","title":"DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Image","created":"2022-09-27","cited_by_count":26},{"id":"2405.11867","title":"Depth Prompting for Sensor-Agnostic Depth Estimation","created":"2024-05-20","cited_by_count":26},{"id":"2210.10758","title":"GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs","created":"2022-10-19","cited_by_count":23},{"id":"2211.08658","title":"Consistent Direct Time-of-Flight Video Depth Super-Resolution","created":"2022-11-16","cited_by_count":16},{"id":"2406.06679","title":"PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation","created":"2024-06-10","cited_by_count":16},{"id":"2311.02778","title":"MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesis","created":"2023-11-05","cited_by_count":12},{"id":"2011.11865","title":"Multi-Scale Progressive Fusion Learning for Depth Map Super-Resolution","created":"2020-11-24","cited_by_count":7},{"id":"2207.14466","title":"Towards Domain-agnostic Depth Completion","created":"2022-07-29","cited_by_count":6},{"id":"2409.08277","title":"Depth on Demand: Streaming Dense Depth from a Low Frame Rate Active Sensor","created":"2024-09-12","cited_by_count":2}],"next_cursor":null}