# Drift Robust Non-rigid Optical Flow Enhancement for Long Sequences

arXiv: https://arxiv.org/abs/1603.02252 · HTML: https://mlsanity.com/paper/1603.02252/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2016.

## Built on by (most cited first, 3 of 3)

- [MFT: Long-Term Tracking of Every Pixel](https://mlsanity.com/paper/2305.12998/) (2023)
- [Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting](https://mlsanity.com/paper/2106.10137/) (2021)
- [Temporally Consistent Label Interpolation for Robust Surgical Multi-Task Learning under Challenging Conditions](https://mlsanity.com/paper/2606.26634/) (2026)

## Abstract (arXiv)

It is hard to densely track a nonrigid object in long term, which is a fundamental research issue in the computer vision community. This task often relies on estimating pairwise correspondences between images over time where the error is accumulated and leads to a drift issue. In this paper, we introduce a novel optimization framework with an Anchor Patch constraint. It is supposed to significantly reduce overall errors given long sequences containing non-rigidly deformable objects. Our framework can be applied to any dense tracking algorithm, e.g. optical flow. We demonstrate the success of our approach by showing significant error reduction on 6 popular optical flow algorithms applied to a range of real-world nonrigid benchmarks. We also provide quantitative analysis of our approach given synthetic occlusions and image noise.