# Monocular Depth Estimation Using Cues Inspired by Biological Vision Systems

arXiv: https://arxiv.org/abs/2204.10384 · HTML: https://mlsanity.com/paper/2204.10384/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 21 Apr 2022.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation](https://mlsanity.com/paper/1907.10326/) (2019)
- [High-Resolution Representations for Labeling Pixels and Regions](https://mlsanity.com/paper/1904.04514/) (2019)
- [Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos](https://mlsanity.com/paper/1811.06152/) (2018)
- [How do neural networks see depth in single images?](https://mlsanity.com/paper/1905.07005/) (2019)
- [SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimation](https://mlsanity.com/paper/1905.08598/) (2019)
- [Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation](https://mlsanity.com/paper/2108.08829/) (2021)
- [DESC: Domain Adaptation for Depth Estimation via Semantic Consistency](https://mlsanity.com/paper/2009.01579/) (2020)
- [Learning Depth via Leveraging Semantics: Self-supervised Monocular Depth Estimation with Both Implicit and Explicit Semantic Guidance](https://mlsanity.com/paper/2102.06685/) (2021)
- [Attention-based Context Aggregation Network for Monocular Depth Estimation](https://mlsanity.com/paper/1901.10137/) (2019)

## Built on by (most cited first, 4 of 4)

- [DepthCues: Evaluating Monocular Depth Perception in Large Vision Models](https://mlsanity.com/paper/2411.17385/) (2024)
- [Language-Based Depth Hints for Monocular Depth Estimation](https://mlsanity.com/paper/2403.15551/) (2024)
- [ObjCAViT: Improving Monocular Depth Estimation Using Natural Language Models And Image-Object Cross-Attention](https://mlsanity.com/paper/2211.17232/) (2022)
- [Learning to Project for Cross-Task Knowledge Distillation](https://mlsanity.com/paper/2403.14494/) (2024)

## Abstract (arXiv)

Monocular depth estimation (MDE) aims to transform an RGB image of a scene into a pixelwise depth map from the same camera view. It is fundamentally ill-posed due to missing information: any single image can have been taken from many possible 3D scenes. Part of the MDE task is, therefore, to learn which visual cues in the image can be used for depth estimation, and how. With training data limited by cost of annotation or network capacity limited by computational power, this is challenging. In this work we demonstrate that explicitly injecting visual cue information into the model is beneficial for depth estimation. Following research into biological vision systems, we focus on semantic information and prior knowledge of object sizes and their relations, to emulate the biological cues of relative size, familiar size, and absolute size. We use state-of-the-art semantic and instance segmentation models to provide external information, and exploit language embeddings to encode relational information between classes. We also provide a prior on the average real-world size of objects. This external information overcomes the limitation in data availability, and ensures that the limited capacity of a given network is focused on known-helpful cues, therefore improving performance. We experimentally validate our hypothesis and evaluate the proposed model on the widely used NYUD2 indoor depth estimation benchmark. The results show improvements in depth prediction when the semantic information, size prior and instance size are explicitly provided along with the RGB images, and our method can be easily adapted to any depth estimation system.