# Continual Adaptation for Deep Stereo

arXiv: https://arxiv.org/abs/2007.05233 · HTML: https://mlsanity.com/paper/2007.05233/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2020.

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

- [SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation](https://mlsanity.com/paper/2206.08367/) (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)
- [Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective](https://mlsanity.com/paper/2203.10887/) (2022)
- [NeRF-Supervised Deep Stereo](https://mlsanity.com/paper/2303.17603/) (2023)
- [TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo](https://mlsanity.com/paper/2111.07418/) (2021)
- [Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces](https://mlsanity.com/paper/2301.08245/) (2023)
- [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)
- [Robust Synthetic-to-Real Transfer for Stereo Matching](https://mlsanity.com/paper/2403.07705/) (2024)
- [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)
- [Active Stereo Without Pattern Projector](https://mlsanity.com/paper/2309.12315/) (2023)
- [Test-Time Visual In-Context Tuning](https://mlsanity.com/paper/2503.21777/) (2025)
- [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)
- [PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation](https://mlsanity.com/paper/2207.13340/) (2022)
- [StreamTTO: Efficient Online Test-Time Optimization for Video Depth Completion](https://mlsanity.com/paper/2603.01765/) (2026)
- [Reusable Architecture Growth for Continual Stereo Matching](https://mlsanity.com/paper/2404.00360/) (2024)
- [RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo](https://mlsanity.com/paper/2511.10107/) (2025)
- [Active Stereo in the Wild through Virtual Pattern Projection](https://mlsanity.com/paper/2406.04345/) (2024)
- [Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo](https://mlsanity.com/paper/2604.15312/) (2026)

## Abstract (arXiv)

Depth estimation from stereo images is carried out with unmatched results by convolutional neural networks trained end-to-end to regress dense disparities. Like for most tasks, this is possible if large amounts of labelled samples are available for training, possibly covering the whole data distribution encountered at deployment time. Being such an assumption systematically unmet in real applications, the capacity of adapting to any unseen setting becomes of paramount importance. Purposely, we propose a continual adaptation paradigm for deep stereo networks designed to deal with challenging and ever-changing environments. We design a lightweight and modular architecture, Modularly ADaptive Network (MADNet), and formulate Modular ADaptation algorithms (MAD, MAD++) which permit efficient optimization of independent sub-portions of the entire network. In our paradigm, the learning signals needed to continuously adapt models online can be sourced from self-supervision via right-to-left image warping or from traditional stereo algorithms. With both sources, no other data than the input images being gathered at deployment time are needed. Thus, our network architecture and adaptation algorithms realize the first real-time self-adaptive deep stereo system and pave the way for a new paradigm that can facilitate practical deployment of end-to-end architectures for dense disparity regression.