mlsanityData to 14 Oct 2026

MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation

arXiv 2411.09551 ↗First posted 14 Nov 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

In this work, we present MFTIQ, a novel dense long-term tracking model that advances the Multi-Flow Tracker (MFT) framework to address challenges in point-level visual tracking in video sequences. MFTIQ builds upon the flow-chaining concepts of MFT, integrating an Independent Quality (IQ) module that separates correspondence quality estimation from optical flow computations. This decoupling significantly enhances the accuracy and flexibility of the tracking process, allowing MFTIQ to maintain reliable trajectory predictions even in scenarios of prolonged occlusions and complex dynamics. Designed to be "plug-and-play", MFTIQ can be employed with any off-the-shelf optical flow method without the need for fine-tuning or architectural modifications. Experimental validations on the TAP-Vid Davis dataset show that MFTIQ with RoMa optical flow not only surpasses MFT but also performs comparably to state-of-the-art trackers while having substantially faster processing speed. Code and models available at https://github.com/serycjon/MFTIQ .

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 14 Nov 2024.

Builds on

39 of 61 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  3. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  4. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  5. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  6. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  7. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 957
  8. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
  9. 2023CoTracker: It is Better to Track Togethercited by 522
  10. 2022Kubric: A scalable dataset generatorcited by 381
  11. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 327
  12. 2019A Short Note on the Kinetics-700 Human Action Datasetcited by 310
27 more
  1. 2023TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinementcited by 287
  2. 2018ATOM: Accurate Tracking by Overlap Maximizationcited by 285
  3. 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 275
  4. 2022TAP-Vid: A Benchmark for Tracking Any Point in a Videocited by 263
  5. 2022Particle Video Revisited: Tracking Through Occlusions Using Point Trajectoriescited by 217
  6. 2023Tracking Everything Everywhere All at Oncecited by 193
  7. 2024SpatialTracker: Tracking Any 2D Pixels in 3D Spacecited by 181
  8. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 177
  9. 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 174
  10. 2019MAGSAC++, a fast, reliable and accurate robust estimatorcited by 161
  11. 2023FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimationcited by 114
  12. 2023RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitationcited by 90
  13. 2023VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimationcited by 82
  14. 2023MFT: Long-Term Tracking of Every Pixelcited by 62
  15. 2023Dense Optical Tracking: Connecting the Dotscited by 61
  16. 2020Future Video Synthesis with Object Motion Predictioncited by 57
  17. 2024MemFlow: Optical Flow Estimation and Prediction with Memorycited by 55
  18. 2024TAPTR: Tracking Any Point with Transformers as Detectioncited by 45
  19. 2020Online Invariance Selection for Local Feature Descriptorscited by 41
  20. 2017Planar Object Tracking in the Wild: A Benchmarkcited by 10
  21. 2021Homography Decomposition Networks for Planar Object Trackingcited by 9
  22. 2022HVC-Net: Unifying Homography, Visibility, and Confidence Learning for Planar Object Trackingcited by 7
  23. 2023Planar Object Tracking via Weighted Optical Flowcited by 7
  24. 2024NeuFlow: Real-time, High-accuracy Optical Flow Estimation on Robots Using Edge Devicescited by 7
  25. 2020Multi-object Monocular SLAM for Dynamic Environmentscited by 4
  26. 2023LLA-FLOW: A Lightweight Local Aggregation on Cost Volume for Optical Flow Estimationcited by 2
  27. 2024Dense Matchers for Dense Trackingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 2.

7 papers.

  1. 2025Point Tracking in Surgery--The 2024 Surgical Tattoos in Infrared (STIR) Challengecited by 7
  2. 2025LiteTracker: Leveraging Temporal Causality for Accurate Low-latency Tissue Trackingcited by 5
  3. 2025BleedOrigin: Dynamic Bleeding Source Localization in Endoscopic Submucosal Dissection via Dual-Stage Detection and Trackingcited by 2
  4. 2025Endo-TTAP: Robust Endoscopic Tissue Tracking via Multi-Facet Guided Attention and Hybrid Flow-point Supervisioncited by 1
  5. 2025Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmarkcited by 0
  6. 2026Point Tracking in Surgery--The 2025 Surgical Tattoos in Infrared Challenge (STIRC2025)cited by 0
  7. 2026P-SRM: Selective Recovery of Rejected Predictions in Visual Trackingcited by 0