# Visualization of Convolutional Neural Networks for Monocular Depth Estimation

arXiv: https://arxiv.org/abs/1904.03380 · HTML: https://mlsanity.com/paper/1904.03380/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2019.

## Built on by (most cited first, 24 of 24)

- [Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging](https://mlsanity.com/paper/2105.14021/) (2021)
- [Toward Practical Monocular Indoor Depth Estimation](https://mlsanity.com/paper/2112.02306/) (2021)
- [Single Image Depth Estimation: An Overview](https://mlsanity.com/paper/2104.06456/) (2021)
- [Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNN](https://mlsanity.com/paper/2308.08333/) (2023)
- [Deep Depth Completion from Extremely Sparse Data: A Survey](https://mlsanity.com/paper/2205.05335/) (2022)
- [GEDepth: Ground Embedding for Monocular Depth Estimation](https://mlsanity.com/paper/2309.09975/) (2023)
- [S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation](https://mlsanity.com/paper/2104.00877/) (2021)
- [EVEN: An Event-Based Framework for Monocular Depth Estimation at Adverse Night Conditions](https://mlsanity.com/paper/2302.03860/) (2023)
- [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)
- [Towards Interpretable Deep Networks for Monocular Depth Estimation](https://mlsanity.com/paper/2108.05312/) (2021)
- [Depth Completion using Geometry-Aware Embedding](https://mlsanity.com/paper/2203.10912/) (2022)
- [Dense Depth Distillation with Out-of-Distribution Simulated Images](https://mlsanity.com/paper/2208.12464/) (2022)
- [A Study on the Generality of Neural Network Structures for Monocular Depth Estimation](https://mlsanity.com/paper/2301.03169/) (2023)
- [Deep Depth Estimation from Thermal Image: Dataset, Benchmark, and Challenges](https://mlsanity.com/paper/2503.22060/) (2025)
- [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)
- [End-to-end deep learning for directly estimating grape yield from ground-based imagery](https://mlsanity.com/paper/2208.02394/) (2022)
- [Deep Bayesian Future Fusion for Self-Supervised, High-Resolution, Off-Road Mapping](https://mlsanity.com/paper/2403.11876/) (2024)
- [The Devil is in the Edges: Monocular Depth Estimation with Edge-aware Consistency Fusion](https://mlsanity.com/paper/2404.00373/) (2024)
- [ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimation](https://mlsanity.com/paper/2309.14744/) (2023)
- [Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks](https://mlsanity.com/paper/2605.08320/) (2026)
- [Lightweight Monocular Depth Estimation with an Edge Guided Network](https://mlsanity.com/paper/2209.14829/) (2022)
- [Depth Insight -- Contribution of Different Features to Indoor Single-image Depth Estimation](https://mlsanity.com/paper/2311.10042/) (2023)

## Abstract (arXiv)

Recently, convolutional neural networks (CNNs) have shown great success on the task of monocular depth estimation. A fundamental yet unanswered question is: how CNNs can infer depth from a single image. Toward answering this question, we consider visualization of inference of a CNN by identifying relevant pixels of an input image to depth estimation. We formulate it as an optimization problem of identifying the smallest number of image pixels from which the CNN can estimate a depth map with the minimum difference from the estimate from the entire image. To cope with a difficulty with optimization through a deep CNN, we propose to use another network to predict those relevant image pixels in a forward computation. In our experiments, we first show the effectiveness of this approach, and then apply it to different depth estimation networks on indoor and outdoor scene datasets. The results provide several findings that help exploration of the above question.