# Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction

arXiv: https://arxiv.org/abs/1903.07309 · HTML: https://mlsanity.com/paper/1903.07309/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Mar 2019.

## Built on by (most cited first, 30 of 44)

- [Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging](https://mlsanity.com/paper/2105.14021/) (2021)
- [Unsupervised Depth Completion with Calibrated Backprojection Layers](https://mlsanity.com/paper/2108.10531/) (2021)
- [Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2109.12484/) (2021)
- [Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth](https://mlsanity.com/paper/2203.15174/) (2022)
- [Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry](https://mlsanity.com/paper/2112.08177/) (2021)
- [Learning Topology from Synthetic Data for Unsupervised Depth Completion](https://mlsanity.com/paper/2106.02994/) (2021)
- [WorDepth: Variational Language Prior for Monocular Depth Estimation](https://mlsanity.com/paper/2404.03635/) (2024)
- [PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes](https://mlsanity.com/paper/2210.01612/) (2022)
- [Not Just Streaks: Towards Ground Truth for Single Image Deraining](https://mlsanity.com/paper/2206.10779/) (2022)
- [Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution](https://mlsanity.com/paper/2103.12955/) (2021)
- [An Adaptive Framework for Learning Unsupervised Depth Completion](https://mlsanity.com/paper/2106.03010/) (2021)
- [Test-Time Adaptation for Depth Completion](https://mlsanity.com/paper/2402.03312/) (2024)
- [Monitored Distillation for Positive Congruent Depth Completion](https://mlsanity.com/paper/2203.16034/) (2022)
- [RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions](https://mlsanity.com/paper/2410.02924/) (2024)
- [Stereoscopic Universal Perturbations across Different Architectures and Datasets](https://mlsanity.com/paper/2112.06116/) (2021)
- [Robust Depth Completion with Uncertainty-Driven Loss Functions](https://mlsanity.com/paper/2112.07895/) (2021)
- [Enhancing Diffusion Models with 3D Perspective Geometry Constraints](https://mlsanity.com/paper/2312.00944/) (2023)
- [AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation](https://mlsanity.com/paper/2310.09739/) (2023)
- [Heteroscedastic Uncertainty Estimation Framework for Unsupervised Registration](https://mlsanity.com/paper/2312.00836/) (2023)
- [Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR](https://mlsanity.com/paper/2109.09628/) (2021)
- [3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video](https://mlsanity.com/paper/2112.03045/) (2021)
- [ProtoDepth: Unsupervised Continual Depth Completion with Prototypes](https://mlsanity.com/paper/2503.12745/) (2025)
- [Self-supervised Visual-LiDAR Odometry with Flip Consistency](https://mlsanity.com/paper/2101.01322/) (2021)
- [Adaptive Correspondence Scoring for Unsupervised Medical Image Registration](https://mlsanity.com/paper/2312.00837/) (2023)
- [Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens](https://mlsanity.com/paper/2508.04928/) (2025)
- [Joint Self-supervised Depth and Optical Flow Estimation towards Dynamic Objects](https://mlsanity.com/paper/2310.00011/) (2023)
- [All-day Depth Completion](https://mlsanity.com/paper/2405.17315/) (2024)
- [Learning Occlusion-Aware Coarse-to-Fine Depth Map for Self-supervised Monocular Depth Estimation](https://mlsanity.com/paper/2203.10925/) (2022)
- [Layered Depth Refinement with Mask Guidance](https://mlsanity.com/paper/2206.03048/) (2022)
- [Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Training](https://mlsanity.com/paper/2411.02149/) (2024)

## Abstract (arXiv)

Supervised learning methods to infer (hypothesize) depth of a scene from a single image require costly per-pixel ground-truth. We follow a geometric approach that exploits abundant stereo imagery to learn a model to hypothesize scene structure without direct supervision. Although we train a network with stereo pairs, we only require a single image at test time to hypothesize disparity or depth. We propose a novel objective function that exploits the bilateral cyclic relationship between the left and right disparities and we introduce an adaptive regularization scheme that allows the network to handle both the co-visible and occluded regions in a stereo pair. This process ultimately produces a model to generate hypotheses for the 3-dimensional structure of the scene as viewed in a single image. When used to generate a single (most probable) estimate of depth, our method outperforms state-of-the-art unsupervised monocular depth prediction methods on the KITTI benchmarks. We show that our method generalizes well by applying our models trained on KITTI to the Make3d dataset.