# Depth Estimation using Weighted-loss and Transfer Learning

arXiv: https://arxiv.org/abs/2404.07686 · HTML: https://mlsanity.com/paper/2404.07686/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 11 Apr 2024.

## Builds on (most cited first, 15 of 15)

- [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)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [Atlas: End-to-End 3D Scene Reconstruction from Posed Images](https://mlsanity.com/paper/2003.10432/) (2020)
- [High Quality Monocular Depth Estimation via Transfer Learning](https://mlsanity.com/paper/1812.11941/) (2018)
- [P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior](https://mlsanity.com/paper/2204.02091/) (2022)
- [Monocular Depth Estimation Based On Deep Learning: An Overview](https://mlsanity.com/paper/2003.06620/) (2020)
- [Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networks](https://mlsanity.com/paper/1809.00646/) (2018)
- [Monocular Depth Estimation with Hierarchical Fusion of Dilated CNNs and Soft-Weighted-Sum Inference](https://mlsanity.com/paper/1708.02287/) (2017)
- [A Neural Network for Detailed Human Depth Estimation from a Single Image](https://mlsanity.com/paper/1910.01275/) (2019)
- [Depth estimation using structured light flow -- analysis of projected pattern flow on an object's surface --](https://mlsanity.com/paper/1710.00513/) (2017)
- [Depth-only Object Tracking](https://mlsanity.com/paper/2110.11679/) (2021)
- [MobileXNet: An Efficient Convolutional Neural Network for Monocular Depth Estimation](https://mlsanity.com/paper/2111.12334/) (2021)

## Built on by (most cited first, 1 of 1)

- [BertsWin: Resolving Topological Sparsity in 3D Masked Autoencoders via Component-Balanced Structural Optimization](https://mlsanity.com/paper/2512.21769/) (2025)

## Abstract (arXiv)

Depth estimation from 2D images is a common computer vision task that has applications in many fields including autonomous vehicles, scene understanding and robotics. The accuracy of a supervised depth estimation method mainly relies on the chosen loss function, the model architecture, quality of data and performance metrics. In this study, we propose a simplified and adaptable approach to improve depth estimation accuracy using transfer learning and an optimized loss function. The optimized loss function is a combination of weighted losses to which enhance robustness and generalization: Mean Absolute Error (MAE), Edge Loss and Structural Similarity Index (SSIM). We use a grid search and a random search method to find optimized weights for the losses, which leads to an improved model. We explore multiple encoder-decoder-based models including DenseNet121, DenseNet169, DenseNet201, and EfficientNet for the supervised depth estimation model on NYU Depth Dataset v2. We observe that the EfficientNet model, pre-trained on ImageNet for classification when used as an encoder, with a simple upsampling decoder, gives the best results in terms of RSME, REL and log10: 0.386, 0.113 and 0.049, respectively. We also perform a qualitative analysis which illustrates that our model produces depth maps that closely resemble ground truth, even in cases where the ground truth is flawed. The results indicate significant improvements in accuracy and robustness, with EfficientNet being the most successful architecture.