{"total":1201,"rows":[{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803,"area":null},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567,"area":null},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422,"area":null},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360,"area":null},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175,"area":null},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044,"area":null},{"id":"2107.02791","title":"Depth-supervised NeRF: Fewer Views and Faster Training for Free","created":"2021-07-06","cited_by_count":735,"area":null},{"id":"2312.12337","title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","created":"2023-12-19","cited_by_count":684,"area":null},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657,"area":null},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629,"area":null},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548,"area":null},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492,"area":null},{"id":"2206.00665","title":"MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction","created":"2022-06-01","cited_by_count":470,"area":null},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464,"area":null},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442,"area":null},{"id":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420,"area":null},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404,"area":null},{"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,"area":null},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382,"area":null},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367,"area":null},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365,"area":null},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337,"area":null},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336,"area":null},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314,"area":null},{"id":"2302.10663","title":"RealFusion: 360{\\deg} Reconstruction of Any Object from a Single Image","created":"2023-02-21","cited_by_count":306,"area":null},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299,"area":null},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291,"area":null},{"id":"2410.13862","title":"DepthSplat: Connecting Gaussian Splatting and Depth","created":"2024-10-17","cited_by_count":286,"area":null},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275,"area":null},{"id":"2205.02833","title":"Cross-view Transformers for real-time Map-view Semantic Segmentation","created":"2022-05-05","cited_by_count":264,"area":null},{"id":"2507.02546","title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","created":"2025-07-03","cited_by_count":261,"area":null},{"id":"2403.06912","title":"DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization","created":"2024-03-11","cited_by_count":256,"area":null},{"id":"2212.07388","title":"NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior","created":"2022-12-14","cited_by_count":235,"area":null},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228,"area":null},{"id":"2211.11082","title":"DynIBaR: Neural Dynamic Image-Based Rendering","created":"2022-11-20","cited_by_count":224,"area":null},{"id":"2406.12080","title":"A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets","created":"2024-06-17","cited_by_count":216,"area":null},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215,"area":null},{"id":"2111.01007","title":"Projected GANs Converge Faster","created":"2021-11-01","cited_by_count":208,"area":null},{"id":"2412.12392","title":"MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors","created":"2024-12-16","cited_by_count":205,"area":null},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204,"area":null},{"id":"2301.02239","title":"Robust Dynamic Radiance Fields","created":"2023-01-05","cited_by_count":194,"area":null},{"id":"2306.05422","title":"Tracking Everything Everywhere All at Once","created":"2023-06-08","cited_by_count":193,"area":null},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177,"area":null},{"id":"2307.14460","title":"MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation","created":"2023-07-26","cited_by_count":174,"area":null},{"id":"2502.20110","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","created":"2025-02-27","cited_by_count":173,"area":null},{"id":"2302.03594","title":"NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM","created":"2023-02-07","cited_by_count":164,"area":null},{"id":"2302.01133","title":"SceneScape: Text-Driven Consistent Scene Generation","created":"2023-02-02","cited_by_count":160,"area":null},{"id":"2312.03884","title":"WonderJourney: Going from Anywhere to Everywhere","created":"2023-12-06","cited_by_count":158,"area":null},{"id":"2504.00983","title":"WorldScore: A Unified Evaluation Benchmark for World Generation","created":"2025-04-01","cited_by_count":156,"area":null},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148,"area":null},{"id":"2302.12827","title":"Decoupling Human and Camera Motion from Videos in the Wild","created":"2023-02-24","cited_by_count":142,"area":null},{"id":"2312.00206","title":"SparseGS: Sparse View Synthesis using 3D Gaussian Splatting","created":"2023-11-30","cited_by_count":134,"area":null},{"id":"2103.14910","title":"MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis","created":"2021-03-27","cited_by_count":133,"area":null},{"id":"2306.00943","title":"Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance","created":"2023-06-01","cited_by_count":129,"area":null},{"id":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127,"area":null},{"id":"2112.13762","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","created":"2021-12-27","cited_by_count":122,"area":null},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119,"area":null},{"id":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117,"area":null},{"id":"2403.10516","title":"FeatUp: A Model-Agnostic Framework for Features at Any Resolution","created":"2024-03-15","cited_by_count":116,"area":null},{"id":"2406.04343","title":"Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image","created":"2024-06-06","cited_by_count":116,"area":null},{"id":"2210.05494","title":"Map-free Visual Relocalization: Metric Pose Relative to a Single Image","created":"2022-10-11","cited_by_count":114,"area":null},{"id":"2210.04888","title":"EVA3D: Compositional 3D Human Generation from 2D Image Collections","created":"2022-10-10","cited_by_count":111,"area":null},{"id":"2204.02091","title":"P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior","created":"2022-04-05","cited_by_count":107,"area":null},{"id":"2105.14021","title":"Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging","created":"2021-05-28","cited_by_count":104,"area":null},{"id":"2402.07181","title":"3D Gaussian as a New Era: A Survey","created":"2024-02-11","cited_by_count":104,"area":null},{"id":"2303.13791","title":"Progressively Optimized Local Radiance Fields for Robust View Synthesis","created":"2023-03-24","cited_by_count":103,"area":null},{"id":"2306.17253","title":"Towards Zero-Shot Scale-Aware Monocular Depth Estimation","created":"2023-06-29","cited_by_count":101,"area":null},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100,"area":null},{"id":"2203.15132","title":"LocalBins: Improving Depth Estimation by Learning Local Distributions","created":"2022-03-28","cited_by_count":94,"area":null},{"id":"2208.12697","title":"Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction","created":"2022-08-26","cited_by_count":94,"area":null},{"id":"2204.07640","title":"Event-aided Direct Sparse Odometry","created":"2022-04-15","cited_by_count":92,"area":null},{"id":"2207.09137","title":"ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild","created":"2022-07-19","cited_by_count":92,"area":null},{"id":"2503.24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training","created":"2025-03-31","cited_by_count":91,"area":null},{"id":"2307.06940","title":"Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation","created":"2023-07-13","cited_by_count":90,"area":null},{"id":"2311.17061","title":"HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting","created":"2023-11-28","cited_by_count":89,"area":null},{"id":"2412.09621","title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","created":"2024-12-12","cited_by_count":89,"area":null},{"id":"2105.05994","title":"Neural Trajectory Fields for Dynamic Novel View Synthesis","created":"2021-05-12","cited_by_count":86,"area":null},{"id":"2308.09718","title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training","created":"2023-08-18","cited_by_count":86,"area":null},{"id":"2108.11353","title":"Multi-Task Self-Training for Learning General Representations","created":"2021-08-25","cited_by_count":85,"area":null},{"id":"2203.12691","title":"Learning to generate line drawings that convey geometry and semantics","created":"2022-03-23","cited_by_count":83,"area":null},{"id":"2208.14743","title":"SimpleRecon: 3D Reconstruction Without 3D Convolutions","created":"2022-08-31","cited_by_count":83,"area":null},{"id":"2207.11148","title":"InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images","created":"2022-07-22","cited_by_count":82,"area":null},{"id":"2412.03079","title":"Align3R: Aligned Monocular Depth Estimation for Dynamic Videos","created":"2024-12-04","cited_by_count":79,"area":null},{"id":"2308.14749","title":"MagicEdit: High-Fidelity and Temporally Coherent Video Editing","created":"2023-08-28","cited_by_count":76,"area":null},{"id":"2309.00610","title":"CityDreamer: Compositional Generative Model of Unbounded 3D Cities","created":"2023-09-01","cited_by_count":76,"area":null},{"id":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76,"area":null},{"id":"2402.11095","title":"GIM: Learning Generalizable Image Matcher From Internet Videos","created":"2024-02-16","cited_by_count":75,"area":null},{"id":"2412.14015","title":"Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation","created":"2024-12-18","cited_by_count":74,"area":null},{"id":"2405.17251","title":"GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping","created":"2024-05-27","cited_by_count":73,"area":null},{"id":"2302.01330","title":"SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections","created":"2023-02-02","cited_by_count":72,"area":null},{"id":"2310.19909","title":"Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks","created":"2023-10-30","cited_by_count":72,"area":null},{"id":"2402.13255","title":"How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Survey","created":"2024-02-20","cited_by_count":72,"area":null},{"id":"2407.05921","title":"TAPVid-3D: A Benchmark for Tracking Any Point in 3D","created":"2024-07-08","cited_by_count":72,"area":null},{"id":"2105.11610","title":"Unsupervised Scale-consistent Depth Learning from Video","created":"2021-05-25","cited_by_count":69,"area":null},{"id":"2108.02158","title":"Physics-based Noise Modeling for Extreme Low-light Photography","created":"2021-08-04","cited_by_count":67,"area":null},{"id":"2110.09482","title":"Self-Supervised Monocular Depth Estimation with Internal Feature Fusion","created":"2021-10-18","cited_by_count":67,"area":null}],"next_cursor":"100"}