# Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasets

arXiv: https://arxiv.org/abs/2007.11256 · HTML: https://mlsanity.com/paper/2007.11256/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2020.

## Built on by (most cited first, 14 of 14)

- [Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging](https://mlsanity.com/paper/2105.14021/) (2021)
- [Multi-Space Alignments Towards Universal LiDAR Segmentation](https://mlsanity.com/paper/2405.01538/) (2024)
- [NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction](https://mlsanity.com/paper/2211.16799/) (2022)
- [From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction](https://mlsanity.com/paper/2203.08122/) (2022)
- [Boosting Light-Weight Depth Estimation Via Knowledge Distillation](https://mlsanity.com/paper/2105.06143/) (2021)
- [Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey](https://mlsanity.com/paper/2406.19675/) (2024)
- [EdgeConv with Attention Module for Monocular Depth Estimation](https://mlsanity.com/paper/2106.08615/) (2021)
- [Layered Depth Refinement with Mask Guidance](https://mlsanity.com/paper/2206.03048/) (2022)
- [Pyramid Feature Attention Network for Monocular Depth Prediction](https://mlsanity.com/paper/2403.01440/) (2024)
- [The Devil is in the Edges: Monocular Depth Estimation with Edge-aware Consistency Fusion](https://mlsanity.com/paper/2404.00373/) (2024)
- [CI-Net: Contextual Information for Joint Semantic Segmentation and Depth Estimation](https://mlsanity.com/paper/2107.13800/) (2021)
- [Object-aware Monocular Depth Prediction with Instance Convolutions](https://mlsanity.com/paper/2112.01521/) (2021)
- [SS3D: End2End Self-Supervised 3D from Web Videos](https://mlsanity.com/paper/2604.22686/) (2026)
- [Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks](https://mlsanity.com/paper/2605.08320/) (2026)

## Abstract (arXiv)

Monocular depth estimation plays a crucial role in 3D recognition and understanding. One key limitation of existing approaches lies in their lack of structural information exploitation, which leads to inaccurate spatial layout, discontinuous surface, and ambiguous boundaries. In this paper, we tackle this problem in three aspects. First, to exploit the spatial relationship of visual features, we propose a structure-aware neural network with spatial attention blocks. These blocks guide the network attention to global structures or local details across different feature layers. Second, we introduce a global focal relative loss for uniform point pairs to enhance spatial constraint in the prediction, and explicitly increase the penalty on errors in depth-wise discontinuous regions, which helps preserve the sharpness of estimation results. Finally, based on analysis of failure cases for prior methods, we collect a new Hard Case (HC) Depth dataset of challenging scenes, such as special lighting conditions, dynamic objects, and tilted camera angles. The new dataset is leveraged by an informed learning curriculum that mixes training examples incrementally to handle diverse data distributions. Experimental results show that our method outperforms state-of-the-art approaches by a large margin in terms of both prediction accuracy on NYUDv2 dataset and generalization performance on unseen datasets.