mlsanityData to 14 Oct 2026

Planar Object Tracking via Weighted Optical Flow

arXiv 2301.10057 ↗First posted 24 Jan 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

We propose WOFT -- a novel method for planar object tracking that estimates a full 8 degrees-of-freedom pose, i.e. the homography w.r.t. a reference view. The method uses a novel module that leverages dense optical flow and assigns a weight to each optical flow correspondence, estimating a homography by weighted least squares in a fully differentiable manner. The trained module assigns zero weights to incorrect correspondences (outliers) in most cases, making the method robust and eliminating the need of the typically used non-differentiable robust estimators like RANSAC. The proposed weighted optical flow tracker (WOFT) achieves state-of-the-art performance on two benchmarks, POT-210 and POIC, tracking consistently well across a wide range of scenarios.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 19 of its 53 references that are in the map. First posted on arXiv 24 Jan 2023.

Builds on

19 of 53 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  5. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  6. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 957
  7. 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 429
  8. 2018YouTube-VOS: A Large-Scale Video Object Segmentation Benchmarkcited by 383
  9. 2018TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wildcited by 343
  10. 2017Convolutional neural network architecture for geometric matchingcited by 138
  11. 2016Deep Image Homography Estimationcited by 136
  12. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
7 more
  1. 2017YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Videocited by 109
  2. 2019A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularizationcited by 76
  3. 2017Unsupervised Deep Homography: A Fast and Robust Homography Estimation Modelcited by 75
  4. 2019GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNscited by 47
  5. 2020Online Invariance Selection for Local Feature Descriptorscited by 41
  6. 2017Planar Object Tracking in the Wild: A Benchmarkcited by 10
  7. 2021Homography Decomposition Networks for Planar Object Trackingcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 2; 2026: 2.

7 papers.

  1. 2023MFT: Long-Term Tracking of Every Pixelcited by 62
  2. 2024MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimationcited by 7
  3. 2023PlanarTrack: A Large-scale Challenging Benchmark for Planar Object Trackingcited by 2
  4. 2025Perturbed State Space Feature Encoders for Optical Flow with Event Camerascited by 2
  5. 2025PlanarTrack: A high-quality and challenging benchmark for large-scale planar object trackingcited by 2
  6. 2026From Contrast to Consistency: Rethinking Event-based Continuous-Time Optical Flow Estimationcited by 1
  7. 2026Segmentation-Guided Homography Estimation for Long-Term Planar Trackingcited by 0