# Semi-Supervised Adversarial Monocular Depth Estimation

arXiv: https://arxiv.org/abs/1908.02126 · HTML: https://mlsanity.com/paper/1908.02126/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2019.

## Built on by (most cited first, 11 of 11)

- [CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching](https://mlsanity.com/paper/2104.04314/) (2021)
- [Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey](https://mlsanity.com/paper/2406.19675/) (2024)
- [Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator](https://mlsanity.com/paper/2502.19204/) (2025)
- [The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation](https://mlsanity.com/paper/2307.15061/) (2023)
- [G2-MonoDepth: A General Framework of Generalized Depth Inference from Monocular RGB+X Data](https://mlsanity.com/paper/2310.15422/) (2023)
- [3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions](https://mlsanity.com/paper/2404.04823/) (2024)
- [3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling](https://mlsanity.com/paper/2209.09231/) (2022)
- [Bidirectional Semi-supervised Dual-branch CNN for Robust 3D Reconstruction of Stereo Endoscopic Images via Adaptive Cross and Parallel Supervisions](https://mlsanity.com/paper/2210.08291/) (2022)
- [Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data](https://mlsanity.com/paper/2109.11573/) (2021)
- [Rethinking Skip Connections in Encoder-decoder Networks for Monocular Depth Estimation](https://mlsanity.com/paper/2208.13441/) (2022)
- [StruMPL: Multi-task Dense Regression under Disjoint Partial Supervision and MNAR Labels](https://mlsanity.com/paper/2605.19931/) (2026)

## Abstract (arXiv)

In this paper, we address the problem of monocular depth estimation when only a limited number of training image-depth pairs are available. To achieve a high regression accuracy, the state-of-the-art estimation methods rely on CNNs trained with a large number of image-depth pairs, which are prohibitively costly or even infeasible to acquire. Aiming to break the curse of such expensive data collections, we propose a semi-supervised adversarial learning framework that only utilizes a small number of image-depth pairs in conjunction with a large number of easily-available monocular images to achieve high performance. In particular, we use one generator to regress the depth and two discriminators to evaluate the predicted depth , i.e., one inspects the image-depth pair while the other inspects the depth channel alone. These two discriminators provide their feedbacks to the generator as the loss to generate more realistic and accurate depth predictions. Experiments show that the proposed approach can (1) improve most state-of-the-art models on the NYUD v2 dataset by effectively leveraging additional unlabeled data sources; (2) reach state-of-the-art accuracy when the training set is small, e.g., on the Make3D dataset; (3) adapt well to an unseen new dataset (Make3D in our case) after training on an annotated dataset (KITTI in our case).