# Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation

arXiv: https://arxiv.org/abs/2008.07130 · HTML: https://mlsanity.com/paper/2008.07130/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2020.

## Built on by (most cited first, 30 of 34)

- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping](https://mlsanity.com/paper/2105.07014/) (2021)
- [Multi-Frame Self-Supervised Depth with Transformers](https://mlsanity.com/paper/2204.07616/) (2022)
- [Open Challenges in Deep Stereo: the Booster Dataset](https://mlsanity.com/paper/2206.04671/) (2022)
- [Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail](https://mlsanity.com/paper/2412.04472/) (2024)
- [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)
- [A Survey on Deep Stereo Matching in the Twenties](https://mlsanity.com/paper/2407.07816/) (2024)
- [Digging Into Uncertainty-based Pseudo-label for Robust Stereo Matching](https://mlsanity.com/paper/2307.16509/) (2023)
- [Neural Disparity Refinement for Arbitrary Resolution Stereo](https://mlsanity.com/paper/2110.15367/) (2021)
- [Stereo Matching by Self-supervision of Multiscopic Vision](https://mlsanity.com/paper/2104.04170/) (2021)
- [Federated Online Adaptation for Deep Stereo](https://mlsanity.com/paper/2405.14873/) (2024)
- [Unsupervised confidence for LiDAR depth maps and applications](https://mlsanity.com/paper/2210.03118/) (2022)
- [Diving into the Fusion of Monocular Priors for Generalized Stereo Matching](https://mlsanity.com/paper/2505.14414/) (2025)
- [StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes](https://mlsanity.com/paper/2509.16415/) (2025)
- [Two-in-One Depth: Bridging the Gap Between Monocular and Binocular Self-supervised Depth Estimation](https://mlsanity.com/paper/2309.00933/) (2023)
- [Active Stereo Without Pattern Projector](https://mlsanity.com/paper/2309.12315/) (2023)
- [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)
- [Degradation-agnostic Correspondence from Resolution-asymmetric Stereo](https://mlsanity.com/paper/2204.01429/) (2022)
- [RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions](https://mlsanity.com/paper/2509.19165/) (2025)
- [Geometry-Aware Unsupervised Domain Adaptation for Stereo Matching](https://mlsanity.com/paper/2103.14333/) (2021)
- [Semi-Supervised Disparity Estimation with Deep Feature Reconstruction](https://mlsanity.com/paper/2106.00318/) (2021)
- [Achieving Domain Robustness in Stereo Matching Networks by Removing Shortcut Learning](https://mlsanity.com/paper/2106.08486/) (2021)
- [FCDSN-DC: An Accurate and Lightweight Convolutional Neural Network for Stereo Estimation with Depth Completion](https://mlsanity.com/paper/2209.06525/) (2022)
- [RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo](https://mlsanity.com/paper/2511.10107/) (2025)
- [ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device](https://mlsanity.com/paper/2607.08771/) (2026)
- [Active Stereo in the Wild through Virtual Pattern Projection](https://mlsanity.com/paper/2406.04345/) (2024)
- [A Noncontact Technique for Wave Measurement Based on Thermal Stereography and Deep Learning](https://mlsanity.com/paper/2408.10670/) (2024)

## Abstract (arXiv)

In many fields, self-supervised learning solutions are rapidly evolving and filling the gap with supervised approaches. This fact occurs for depth estimation based on either monocular or stereo, with the latter often providing a valid source of self-supervision for the former. In contrast, to soften typical stereo artefacts, we propose a novel self-supervised paradigm reversing the link between the two. Purposely, in order to train deep stereo networks, we distill knowledge through a monocular completion network. This architecture exploits single-image clues and few sparse points, sourced by traditional stereo algorithms, to estimate dense yet accurate disparity maps by means of a consensus mechanism over multiple estimations. We thoroughly evaluate with popular stereo datasets the impact of different supervisory signals showing how stereo networks trained with our paradigm outperform existing self-supervised frameworks. Finally, our proposal achieves notable generalization capabilities dealing with domain shift issues. Code available at https://github.com/FilippoAleotti/Reversing