# Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence

arXiv: https://arxiv.org/abs/1905.09265 · HTML: https://mlsanity.com/paper/1905.09265/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2019.

## Built on by (most cited first, 23 of 23)

- [Open Challenges in Deep Stereo: the Booster Dataset](https://mlsanity.com/paper/2206.04671/) (2022)
- [NeRF-Supervised Deep Stereo](https://mlsanity.com/paper/2303.17603/) (2023)
- [Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces](https://mlsanity.com/paper/2301.08245/) (2023)
- [PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss](https://mlsanity.com/paper/2103.07362/) (2021)
- [Self-Supervised Multi-Frame Monocular Scene Flow](https://mlsanity.com/paper/2105.02216/) (2021)
- [DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images](https://mlsanity.com/paper/2103.02772/) (2021)
- [Semi-supervised Multi-task Learning for Semantics and Depth](https://mlsanity.com/paper/2110.07197/) (2021)
- [Zero-Shot Monocular Scene Flow Estimation in the Wild](https://mlsanity.com/paper/2501.10357/) (2025)
- [Neural Disparity Refinement for Arbitrary Resolution Stereo](https://mlsanity.com/paper/2110.15367/) (2021)
- [3D Object Detection with a Self-supervised Lidar Scene Flow Backbone](https://mlsanity.com/paper/2205.00705/) (2022)
- [TemporalStereo: Efficient Spatial-Temporal Stereo Matching Network](https://mlsanity.com/paper/2211.13755/) (2022)
- [Federated Online Adaptation for Deep Stereo](https://mlsanity.com/paper/2405.14873/) (2024)
- [Active Stereo Without Pattern Projector](https://mlsanity.com/paper/2309.12315/) (2023)
- [Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation](https://mlsanity.com/paper/2106.04195/) (2021)
- [RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluation](https://mlsanity.com/paper/2206.07047/) (2022)
- [Towards Open-World Generation of Stereo Images and Unsupervised Matching](https://mlsanity.com/paper/2503.12720/) (2025)
- [StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptation](https://mlsanity.com/paper/2309.01842/) (2023)
- [UFD-PRiME: Unsupervised Joint Learning of Optical Flow and Stereo Depth through Pixel-Level Rigid Motion Estimation](https://mlsanity.com/paper/2310.04712/) (2023)
- [FluentLip: A Phonemes-Based Two-stage Approach for Audio-Driven Lip Synthesis with Optical Flow Consistency](https://mlsanity.com/paper/2504.04427/) (2025)
- [Optical Flow Dataset Synthesis from Unpaired Images](https://mlsanity.com/paper/2104.02615/) (2021)
- [Skin the sheep not only once: Reusing Various Depth Datasets to Drive the Learning of Optical Flow](https://mlsanity.com/paper/2310.01833/) (2023)
- [Exploring Optical Flow Inclusion into nnU-Net Framework for Surgical Instrument Segmentation](https://mlsanity.com/paper/2403.10216/) (2024)
- [Active Stereo in the Wild through Virtual Pattern Projection](https://mlsanity.com/paper/2406.04345/) (2024)

## Abstract (arXiv)

Stereo matching and flow estimation are two essential tasks for scene understanding, spatially in 3D and temporally in motion. Existing approaches have been focused on the unsupervised setting due to the limited resource to obtain the large-scale ground truth data. To construct a self-learnable objective, co-related tasks are often linked together to form a joint framework. However, the prior work usually utilizes independent networks for each task, thus not allowing to learn shared feature representations across models. In this paper, we propose a single and principled network to jointly learn spatiotemporal correspondence for stereo matching and flow estimation, with a newly designed geometric connection as the unsupervised signal for temporally adjacent stereo pairs. We show that our method performs favorably against several state-of-the-art baselines for both unsupervised depth and flow estimation on the KITTI benchmark dataset.