# 3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video

arXiv: https://arxiv.org/abs/2112.03045 · HTML: https://mlsanity.com/paper/2112.03045/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 67 references that are in the map.
- First posted on arXiv 6 Dec 2021.

## Builds on (most cited first, 30 of 43)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [Softmax Splatting for Video Frame Interpolation](https://mlsanity.com/paper/2003.05534/) (2020)
- [Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video](https://mlsanity.com/paper/1908.10553/) (2019)
- [Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation](https://mlsanity.com/paper/1805.09806/) (2018)
- [D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry](https://mlsanity.com/paper/2003.01060/) (2020)
- [GRF: Learning a General Radiance Field for 3D Representation and Rendering](https://mlsanity.com/paper/2010.04595/) (2020)
- [Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints](https://mlsanity.com/paper/1802.05522/) (2018)
- [Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras](https://mlsanity.com/paper/1904.04998/) (2019)
- [Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields](https://mlsanity.com/paper/1502.07411/) (2015)
- [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction](https://mlsanity.com/paper/1803.03893/) (2018)
- [Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos](https://mlsanity.com/paper/1811.06152/) (2018)
- [Learning Depth from Monocular Videos using Direct Methods](https://mlsanity.com/paper/1712.00175/) (2017)
- [DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency](https://mlsanity.com/paper/1809.01649/) (2018)
- [Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance](https://mlsanity.com/paper/2007.06936/) (2020)
- [Semi-Supervised Deep Learning for Monocular Depth Map Prediction](https://mlsanity.com/paper/1702.02706/) (2017)
- [TartanVO: A Generalizable Learning-based VO](https://mlsanity.com/paper/2011.00359/) (2020)
- [Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding](https://mlsanity.com/paper/1810.06125/) (2018)
- [Towards Better Generalization: Joint Depth-Pose Learning without PoseNet](https://mlsanity.com/paper/2004.01314/) (2020)
- [Unsupervised Monocular Depth Learning in Dynamic Scenes](https://mlsanity.com/paper/2010.16404/) (2020)
- [Learning Monocular Depth by Distilling Cross-domain Stereo Networks](https://mlsanity.com/paper/1808.06586/) (2018)
- [Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation](https://mlsanity.com/paper/1904.01870/) (2019)
- [Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency](https://mlsanity.com/paper/2102.02629/) (2021)
- [LEGO: Learning Edge with Geometry all at Once by Watching Videos](https://mlsanity.com/paper/1803.05648/) (2018)

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

- [D3FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance](https://mlsanity.com/paper/2207.08794/) (2022)
- [SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detection](https://mlsanity.com/paper/2305.07270/) (2023)
- [DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume](https://mlsanity.com/paper/2308.07225/) (2023)
- [DVN-SLAM: Dynamic Visual Neural SLAM Based on Local-Global Encoding](https://mlsanity.com/paper/2403.11776/) (2024)
- [RLSAC: Reinforcement Learning enhanced Sample Consensus for End-to-End Robust Estimation](https://mlsanity.com/paper/2308.05318/) (2023)
- [On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2209.08747/) (2022)
- [Multi-Frame Self-Supervised Depth Estimation with Multi-Scale Feature Fusion in Dynamic Scenes](https://mlsanity.com/paper/2303.14628/) (2023)
- [Unsupervised Visual Odometry and Action Integration for PointGoal Navigation in Indoor Environment](https://mlsanity.com/paper/2210.00413/) (2022)
- [GLASS: Geometry-aware Local Alignment and Structure Synchronization Network for 2D-3D Registration](https://mlsanity.com/paper/2603.26262/) (2026)
- [FA-Depth: Toward Fast and Accurate Self-supervised Monocular Depth Estimation](https://mlsanity.com/paper/2405.10885/) (2024)
- [Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation](https://mlsanity.com/paper/2506.04758/) (2025)

## Abstract (arXiv)

Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video. A novel unsupervised training framework is proposed with 3D hierarchical refinement and augmentation using explicit 3D geometry. In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer. The intermediate view image is proposed and synthesized by warping the pixels in an image with the estimated depth and coarse pose. Then, the residual pose transformation can be estimated from the new view image and the image of the adjacent frame to refine the coarse pose. The iterative refinement is implemented in a differentiable manner in this paper, making the whole framework optimized uniformly. Meanwhile, a new image augmentation method is proposed for the pose estimation by synthesizing a new view image, which creatively augments the pose in 3D space but gets a new augmented 2D image. The experiments on KITTI demonstrate that our depth estimation achieves state-of-the-art performance and even surpasses recent approaches that utilize other auxiliary tasks. Our visual odometry outperforms all recent unsupervised monocular learning-based methods and achieves competitive performance to the geometry-based method, ORB-SLAM2 with back-end optimization.