# Towards Interpretable Deep Networks for Monocular Depth Estimation

arXiv: https://arxiv.org/abs/2108.05312 · HTML: https://mlsanity.com/paper/2108.05312/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 48 references that are in the map.
- First posted on arXiv 11 Aug 2021.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation](https://mlsanity.com/paper/1907.10326/) (2019)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [Sparsity Invariant CNNs](https://mlsanity.com/paper/1708.06500/) (2017)
- [Enforcing geometric constraints of virtual normal for depth prediction](https://mlsanity.com/paper/1907.12209/) (2019)
- [Object Detectors Emerge in Deep Scene CNNs](https://mlsanity.com/paper/1412.6856/) (2014)
- [Interpretable Convolutional Neural Networks](https://mlsanity.com/paper/1710.00935/) (2017)
- [Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries](https://mlsanity.com/paper/1803.08673/) (2018)
- [Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks](https://mlsanity.com/paper/1801.03454/) (2018)
- [Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network](https://mlsanity.com/paper/1808.00150/) (2018)
- [On the importance of single directions for generalization](https://mlsanity.com/paper/1803.06959/) (2018)
- [Learning how to explain neural networks: PatternNet and PatternAttribution](https://mlsanity.com/paper/1705.05598/) (2017)
- [How do neural networks see depth in single images?](https://mlsanity.com/paper/1905.07005/) (2019)
- [The Edge of Depth: Explicit Constraints between Segmentation and Depth](https://mlsanity.com/paper/2004.00171/) (2020)
- [Monocular Depth Estimation Based On Deep Learning: An Overview](https://mlsanity.com/paper/2003.06620/) (2020)
- [Interpreting CNN Knowledge via an Explanatory Graph](https://mlsanity.com/paper/1708.01785/) (2017)

## Built on by (most cited first, 12 of 12)

- [Deep Depth Completion from Extremely Sparse Data: A Survey](https://mlsanity.com/paper/2205.05335/) (2022)
- [ColDE: A Depth Estimation Framework for Colonoscopy Reconstruction](https://mlsanity.com/paper/2111.10371/) (2021)
- [CodedEvents: Optimal Point-Spread-Function Engineering for 3D-Tracking with Event Cameras](https://mlsanity.com/paper/2406.09409/) (2024)
- [Enhancing Monocular Height Estimation via Sparse LiDAR-Guided Correction](https://mlsanity.com/paper/2505.06905/) (2025)
- [Disentangled Latent Transformer for Interpretable Monocular Height Estimation](https://mlsanity.com/paper/2201.06357/) (2022)
- [Neural Contourlet Network for Monocular 360 Depth Estimation](https://mlsanity.com/paper/2208.01817/) (2022)
- [ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimation](https://mlsanity.com/paper/2309.14744/) (2023)
- [LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile Devices](https://mlsanity.com/paper/2209.00961/) (2022)
- [Shedding Light on Depth: Explainability Assessment in Monocular Depth Estimation](https://mlsanity.com/paper/2509.15980/) (2025)
- [Interpretable Vision Transformers in Monocular Depth Estimation via SVDA](https://mlsanity.com/paper/2602.11005/) (2026)
- [PMPNet: Pixel Movement Prediction Network for Monocular Depth Estimation in Dynamic Scenes](https://mlsanity.com/paper/2411.04227/) (2024)
- [Monocular Depth Estimation from a Single Image: Progress and Opportunities](https://mlsanity.com/paper/2609.01172/) (2026)

## Abstract (arXiv)

Deep networks for Monocular Depth Estimation (MDE) have achieved promising performance recently and it is of great importance to further understand the interpretability of these networks. Existing methods attempt to provide posthoc explanations by investigating visual cues, which may not explore the internal representations learned by deep networks. In this paper, we find that some hidden units of the network are selective to certain ranges of depth, and thus such behavior can be served as a way to interpret the internal representations. Based on our observations, we quantify the interpretability of a deep MDE network by the depth selectivity of its hidden units. Moreover, we then propose a method to train interpretable MDE deep networks without changing their original architectures, by assigning a depth range for each unit to select. Experimental results demonstrate that our method is able to enhance the interpretability of deep MDE networks by largely improving the depth selectivity of their units, while not harming or even improving the depth estimation accuracy. We further provide a comprehensive analysis to show the reliability of selective units, the applicability of our method on different layers, models, and datasets, and a demonstration on analysis of model error. Source code and models are available at https://github.com/youzunzhi/InterpretableMDE .