# Self-SuperFlow: Self-supervised Scene Flow Prediction in Stereo Sequences

arXiv: https://arxiv.org/abs/2206.15296 · HTML: https://mlsanity.com/paper/2206.15296/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 30 Jun 2022.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss](https://mlsanity.com/paper/1711.07837/) (2017)
- [What Matters in Unsupervised Optical Flow](https://mlsanity.com/paper/2006.04902/) (2020)
- [Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness](https://mlsanity.com/paper/1608.05842/) (2016)
- [Just Go with the Flow: Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/1912.00497/) (2019)
- [Self-Supervised Monocular Scene Flow Estimation](https://mlsanity.com/paper/2004.04143/) (2020)
- [Self-Supervised Multi-Frame Monocular Scene Flow](https://mlsanity.com/paper/2105.02216/) (2021)
- [PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation](https://mlsanity.com/paper/1904.06116/) (2019)
- [Unsupervised convolutional neural networks for motion estimation](https://mlsanity.com/paper/1601.06087/) (2016)
- [Adversarial Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/2011.00551/) (2020)
- [Guided Optical Flow Learning](https://mlsanity.com/paper/1702.02295/) (2017)
- [TransFlow: Unsupervised Motion Flow by Joint Geometric and Pixel-level Estimation](https://mlsanity.com/paper/1706.00322/) (2017)

## Abstract (arXiv)

In recent years, deep neural networks showed their exceeding capabilities in addressing many computer vision tasks including scene flow prediction. However, most of the advances are dependent on the availability of a vast amount of dense per pixel ground truth annotations, which are very difficult to obtain for real life scenarios. Therefore, synthetic data is often relied upon for supervision, resulting in a representation gap between the training and test data. Even though a great quantity of unlabeled real world data is available, there is a huge lack in self-supervised methods for scene flow prediction. Hence, we explore the extension of a self-supervised loss based on the Census transform and occlusion-aware bidirectional displacements for the problem of scene flow prediction. Regarding the KITTI scene flow benchmark, our method outperforms the corresponding supervised pre-training of the same network and shows improved generalization capabilities while achieving much faster convergence.