# Planar Object Tracking via Weighted Optical Flow

arXiv: https://arxiv.org/abs/2301.10057 · HTML: https://mlsanity.com/paper/2301.10057/

## 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 (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking](https://mlsanity.com/paper/1809.07845/) (2018)
- [YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark](https://mlsanity.com/paper/1809.03327/) (2018)
- [TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild](https://mlsanity.com/paper/1803.10794/) (2018)
- [Convolutional neural network architecture for geometric matching](https://mlsanity.com/paper/1703.05593/) (2017)
- [Deep Image Homography Estimation](https://mlsanity.com/paper/1606.03798/) (2016)
- [SOSNet: Second Order Similarity Regularization for Local Descriptor Learning](https://mlsanity.com/paper/1904.05019/) (2019)
- [YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video](https://mlsanity.com/paper/1702.00824/) (2017)
- [A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization](https://mlsanity.com/paper/1903.07414/) (2019)
- [Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model](https://mlsanity.com/paper/1709.03966/) (2017)
- [GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs](https://mlsanity.com/paper/1911.05932/) (2019)
- [Online Invariance Selection for Local Feature Descriptors](https://mlsanity.com/paper/2007.08988/) (2020)
- [Planar Object Tracking in the Wild: A Benchmark](https://mlsanity.com/paper/1703.07938/) (2017)
- [Homography Decomposition Networks for Planar Object Tracking](https://mlsanity.com/paper/2112.07909/) (2021)

## Built on by (most cited first, 7 of 7)

- [MFT: Long-Term Tracking of Every Pixel](https://mlsanity.com/paper/2305.12998/) (2023)
- [MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation](https://mlsanity.com/paper/2411.09551/) (2024)
- [PlanarTrack: A Large-scale Challenging Benchmark for Planar Object Tracking](https://mlsanity.com/paper/2303.07625/) (2023)
- [Perturbed State Space Feature Encoders for Optical Flow with Event Cameras](https://mlsanity.com/paper/2504.10669/) (2025)
- [PlanarTrack: A high-quality and challenging benchmark for large-scale planar object tracking](https://mlsanity.com/paper/2510.23368/) (2025)
- [From Contrast to Consistency: Rethinking Event-based Continuous-Time Optical Flow Estimation](https://mlsanity.com/paper/2605.25570/) (2026)
- [Segmentation-Guided Homography Estimation for Long-Term Planar Tracking](https://mlsanity.com/paper/2602.19624/) (2026)

## 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.