# Online Adaptation through Meta-Learning for Stereo Depth Estimation

arXiv: https://arxiv.org/abs/1904.08462 · HTML: https://mlsanity.com/paper/1904.08462/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2019.

## Built on by (most cited first, 7 of 7)

- [GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation](https://mlsanity.com/paper/2207.09763/) (2022)
- [On the Road to Online Adaptation for Semantic Image Segmentation](https://mlsanity.com/paper/2203.16195/) (2022)
- [One to Many: Adaptive Instrument Segmentation via Meta Learning and Dynamic Online Adaptation in Robotic Surgical Video](https://mlsanity.com/paper/2103.12988/) (2021)
- [PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation](https://mlsanity.com/paper/2207.13340/) (2022)
- [Meta-Optimization for Higher Model Generalizability in Single-Image Depth Prediction](https://mlsanity.com/paper/2305.07269/) (2023)
- [Boosting Generalizability towards Zero-Shot Cross-Dataset Single-Image Indoor Depth by Meta-Initialization](https://mlsanity.com/paper/2409.02486/) (2024)
- [GeoDiff: Geometry-Guided Diffusion for Metric Depth Estimation](https://mlsanity.com/paper/2510.18291/) (2025)

## Abstract (arXiv)

In this work, we tackle the problem of online adaptation for stereo depth estimation, that consists in continuously adapting a deep network to a target video recordedin an environment different from that of the source training set. To address this problem, we propose a novel Online Meta-Learning model with Adaption (OMLA). Our proposal is based on two main contributions. First, to reducethe domain-shift between source and target feature distributions we introduce an online feature alignment procedurederived from Batch Normalization. Second, we devise a meta-learning approach that exploits feature alignment forfaster convergence in an online learning setting. Additionally, we propose a meta-pre-training algorithm in order toobtain initial network weights on the source dataset whichfacilitate adaptation on future data streams. Experimentally, we show that both OMLA and meta-pre-training helpthe model to adapt faster to a new environment. Our proposal is evaluated on the wellestablished KITTI dataset,where we show that our online method is competitive withstate of the art algorithms trained in a batch setting.