{"total":102,"rows":[{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629,"area":null},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522,"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":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327,"area":null},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327,"area":"diffusion"},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287,"area":null},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276,"area":null},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275,"area":null},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275,"area":null},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263,"area":null},{"id":"2203.11483","title":"Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation","created":"2022-03-22","cited_by_count":197,"area":null},{"id":"2303.01943","title":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","created":"2023-03-03","cited_by_count":172,"area":null},{"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,"area":null},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148,"area":null},{"id":"2306.01923","title":"The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation","created":"2023-06-02","cited_by_count":116,"area":"diffusion"},{"id":"2303.01237","title":"FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation","created":"2023-03-02","cited_by_count":114,"area":null},{"id":"2403.12365","title":"GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation","created":"2024-03-19","cited_by_count":100,"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":"2203.16896","title":"CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow","created":"2022-03-31","cited_by_count":82,"area":null},{"id":"2303.08340","title":"VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation","created":"2023-03-15","cited_by_count":82,"area":null},{"id":"2109.13912","title":"PDC-Net+: Enhanced Probabilistic Dense Correspondence Network","created":"2021-09-28","cited_by_count":80,"area":null},{"id":"2204.08442","title":"Deep Equilibrium Optical Flow Estimation","created":"2022-04-18","cited_by_count":64,"area":null},{"id":"2506.07310","title":"AllTracker: Efficient Dense Point Tracking at High Resolution","created":"2025-06-08","cited_by_count":58,"area":null},{"id":"2205.07514","title":"Residual Local Feature Network for Efficient Super-Resolution","created":"2022-05-16","cited_by_count":53,"area":null},{"id":"2203.13674","title":"Dense Continuous-Time Optical Flow from Events and Frames","created":"2022-03-25","cited_by_count":46,"area":null},{"id":"2202.00732","title":"IFOR: Iterative Flow Minimization for Robotic Object Rearrangement","created":"2022-02-01","cited_by_count":42,"area":null},{"id":"2201.08379","title":"Learning Pixel Trajectories with Multiscale Contrastive Random Walks","created":"2022-01-20","cited_by_count":36,"area":null},{"id":"2303.08384","title":"Rethinking Optical Flow from Geometric Matching Consistent Perspective","created":"2023-03-15","cited_by_count":33,"area":null},{"id":"2201.11279","title":"Revisiting RCAN: Improved Training for Image Super-Resolution","created":"2022-01-27","cited_by_count":32,"area":null},{"id":"2203.10712","title":"Disentangling Architecture and Training for Optical Flow","created":"2022-03-21","cited_by_count":32,"area":null},{"id":"2211.16412","title":"Procedural Image Programs for Representation Learning","created":"2022-11-29","cited_by_count":28,"area":null},{"id":"2206.04790","title":"Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition","created":"2022-06-09","cited_by_count":27,"area":null},{"id":"2303.11011","title":"Learning Optical Flow from Event Camera with Rendered Dataset","created":"2023-03-20","cited_by_count":26,"area":null},{"id":"2312.09523","title":"DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videos","created":"2023-12-15","cited_by_count":25,"area":null},{"id":"2204.07262","title":"Imposing Consistency for Optical Flow Estimation","created":"2022-04-14","cited_by_count":24,"area":null},{"id":"2407.10802","title":"Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation","created":"2024-07-15","cited_by_count":24,"area":null},{"id":"2207.11075","title":"RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos","created":"2022-07-22","cited_by_count":22,"area":null},{"id":"2207.11617","title":"Face Deblurring using Dual Camera Fusion on Mobile Phones","created":"2022-07-23","cited_by_count":18,"area":null},{"id":"2306.08103","title":"Generating Images with 3D Annotations Using Diffusion Models","created":"2023-06-13","cited_by_count":18,"area":"diffusion"},{"id":"2309.16217","title":"GAFlow: Incorporating Gaussian Attention into Optical Flow","created":"2023-09-28","cited_by_count":18,"area":null},{"id":"2303.16493","title":"AnyFlow: Arbitrary Scale Optical Flow with Implicit Neural Representation","created":"2023-03-29","cited_by_count":17,"area":null},{"id":"2307.16586","title":"SAMFlow: Eliminating Any Fragmentation in Optical Flow with Segment Anything Model","created":"2023-07-31","cited_by_count":15,"area":null},{"id":"2303.13569","title":"TinyML: Tools, Applications, Challenges, and Future Research Directions","created":"2023-03-23","cited_by_count":14,"area":null},{"id":"2303.14078","title":"DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling","created":"2023-03-24","cited_by_count":14,"area":null},{"id":"2308.00994","title":"SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems","created":"2023-08-02","cited_by_count":13,"area":null},{"id":"2603.02573","title":"Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels","created":"2026-03-03","cited_by_count":13,"area":null},{"id":"2310.00632","title":"Win-Win: Training High-Resolution Vision Transformers from Two Windows","created":"2023-10-01","cited_by_count":12,"area":null},{"id":"2211.05709","title":"AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies","created":"2022-11-10","cited_by_count":11,"area":null},{"id":"2305.10118","title":"Bridging the Gap: Enhancing the Utility of Synthetic Data via Post-Processing Techniques","created":"2023-05-17","cited_by_count":11,"area":null},{"id":"2403.18092","title":"OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation","created":"2024-03-26","cited_by_count":11,"area":null},{"id":"2409.05688","title":"LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow","created":"2024-09-09","cited_by_count":11,"area":null},{"id":"2212.01762","title":"Self-supervised AutoFlow","created":"2022-12-04","cited_by_count":10,"area":null},{"id":"2409.16288","title":"Self-Supervised Any-Point Tracking by Contrastive Random Walks","created":"2024-09-24","cited_by_count":10,"area":null},{"id":"2505.00209","title":"Direct Motion Models for Assessing Generated Videos","created":"2025-04-30","cited_by_count":10,"area":null},{"id":"2509.05297","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","created":"2025-09-05","cited_by_count":10,"area":null},{"id":"2207.10314","title":"Semi-Supervised Learning of Optical Flow by Flow Supervisor","created":"2022-07-21","cited_by_count":9,"area":null},{"id":"2303.07564","title":"Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flow","created":"2023-03-14","cited_by_count":9,"area":null},{"id":"2206.12657","title":"Enhanced Deep Animation Video Interpolation","created":"2022-06-25","cited_by_count":8,"area":null},{"id":"2405.02608","title":"UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model","created":"2024-05-04","cited_by_count":8,"area":null},{"id":"2306.05691","title":"DIFT: Dynamic Iterative Field Transforms for Memory Efficient Optical Flow","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2309.06714","title":"MPI-Flow: Learning Realistic Optical Flow with Multiplane Images","created":"2023-09-13","cited_by_count":7,"area":null},{"id":"2409.05396","title":"FacialFlowNet: Advancing Facial Optical Flow Estimation with a Diverse Dataset and a Decomposed Model","created":"2024-09-09","cited_by_count":7,"area":null},{"id":"2504.00380","title":"Hierarchical Flow Diffusion for Efficient Frame Interpolation","created":"2025-04-01","cited_by_count":7,"area":"diffusion"},{"id":"2504.16930","title":"What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?","created":"2025-04-23","cited_by_count":7,"area":null},{"id":"2505.09368","title":"RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo","created":"2025-05-14","cited_by_count":7,"area":null},{"id":"2407.07627","title":"Synthetic to Authentic: Transferring Realism to 3D Face Renderings for Boosting Face Recognition","created":"2024-07-10","cited_by_count":5,"area":null},{"id":"2107.10990","title":"Detail Preserving Residual Feature Pyramid Modules for Optical Flow","created":"2021-07-23","cited_by_count":4,"area":null},{"id":"2109.15321","title":"Sensor-Guided Optical Flow","created":"2021-09-30","cited_by_count":4,"area":null},{"id":"2210.00715","title":"WorldGen: A Large Scale Generative Simulator","created":"2022-10-03","cited_by_count":4,"area":null},{"id":"2210.14383","title":"CLIP-FLow: Contrastive Learning by semi-supervised Iterative Pseudo labeling for Optical Flow Estimation","created":"2022-10-25","cited_by_count":4,"area":null},{"id":"2406.01559","title":"Prototypical Transformer as Unified Motion Learners","created":"2024-06-03","cited_by_count":4,"area":null},{"id":"2409.17001","title":"Adverse Weather Optical Flow: Cumulative Homogeneous-Heterogeneous Adaptation","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2306.05442","title":"FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flow","created":"2023-06-08","cited_by_count":3,"area":null},{"id":"2312.01746","title":"Open-DDVM: A Reproduction and Extension of Diffusion Model for Optical Flow Estimation","created":"2023-12-04","cited_by_count":3,"area":"diffusion"},{"id":"2506.03148","title":"Self-Supervised Spatial Correspondence Across Modalities","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2510.10577","title":"Injecting Frame-Event Complementary Fusion into Diffusion for Optical Flow in Challenging Scenes","created":"2025-10-12","cited_by_count":3,"area":"diffusion"},{"id":"2304.14418","title":"SSTM: Spatiotemporal Recurrent Transformers for Multi-frame Optical Flow Estimation","created":"2023-04-26","cited_by_count":2,"area":null},{"id":"2306.05912","title":"Single-Image-Based Deep Learning for Segmentation of Early Esophageal Cancer Lesions","created":"2023-06-09","cited_by_count":2,"area":null},{"id":"2406.12368","title":"MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2507.08400","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2512.00740","title":"Augmented Runtime Collaboration for Self-Organizing Multi-Agent Systems: A Hybrid Bi-Criteria Routing Approach","created":"2025-11-30","cited_by_count":2,"area":"agents"},{"id":"2201.09579","title":"AutoSeg -- Steering the Inductive Biases for Automatic Pathology Segmentation","created":"2022-01-24","cited_by_count":1,"area":null},{"id":"2207.03790","title":"Complementing Brightness Constancy with Deep Networks for Optical Flow Prediction","created":"2022-07-08","cited_by_count":1,"area":null},{"id":"2301.00750","title":"Interactive Control over Temporal Consistency while Stylizing Video Streams","created":"2023-01-02","cited_by_count":1,"area":null},{"id":"2309.11170","title":"AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration","created":"2023-09-20","cited_by_count":1,"area":null},{"id":"2403.08352","title":"Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2504.10201","title":"VibrantLeaves: A principled parametric image generator for training deep restoration models","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2609.01899","title":"TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2211.12748","title":"Dynamic Appearance: A Video Representation for Action Recognition with Joint Training","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2308.07378","title":"The Devil in the Details: Simple and Effective Optical Flow Synthetic Data Generation","created":"2023-08-14","cited_by_count":0,"area":null},{"id":"2409.05531","title":"HMAFlow: Learning More Accurate Optical Flow via Hierarchical Motion Field Alignment","created":"2024-09-09","cited_by_count":0,"area":null},{"id":"2412.13273","title":"CompactFlowNet: Efficient Real-time Optical Flow Estimation on Mobile Devices","created":"2024-12-17","cited_by_count":0,"area":null},{"id":"2502.09434","title":"Redistribute Ensemble Training for Mitigating Memorization in Diffusion Models","created":"2025-02-13","cited_by_count":0,"area":"diffusion"},{"id":"2503.12944","title":"GIFT: Generated Indoor video frames for Texture-less point tracking","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2504.13452","title":"MicroFlow: Domain-Specific Optical Flow for Ground Deformation Estimation in Seismic Events","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2506.22509","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","created":"2025-06-26","cited_by_count":0,"area":"diffusion"},{"id":"2508.11697","title":"Separating Knowledge and Perception with Procedural Data","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2603.28759","title":"FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.10056","title":"U$^{2}$Flow: Uncertainty-Aware Unsupervised Optical Flow Estimation","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2606.07813","title":"MinNav: Minimalist Navigation Using Optical Flow For Active Tiny Aerial Robots","created":"2026-06-05","cited_by_count":0,"area":null}],"next_cursor":"100"}