# Monocular Depth Estimation Using Multi Scale Neural Network And Feature Fusion

arXiv: https://arxiv.org/abs/2009.09934 · HTML: https://mlsanity.com/paper/2009.09934/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2020.

## Built on by (most cited first, 7 of 7)

- [Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey](https://mlsanity.com/paper/2406.19675/) (2024)
- [DMSANet: Dual Multi Scale Attention Network](https://mlsanity.com/paper/2106.08382/) (2021)
- [ViTBIS: Vision Transformer for Biomedical Image Segmentation](https://mlsanity.com/paper/2201.05920/) (2022)
- [SPACE-CLIP: Spatial Perception via Adaptive CLIP Embeddings for Monocular Depth Estimation](https://mlsanity.com/paper/2601.17657/) (2026)
- [AASeg: Attention Aware Network for Real Time Semantic Segmentation](https://mlsanity.com/paper/2108.04349/) (2021)
- [Monocular Depth Estimation with Sharp Boundary](https://mlsanity.com/paper/2110.05885/) (2021)
- [Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2210.03952/) (2022)

## Abstract (arXiv)

Depth estimation from monocular images is a challenging problem in computer vision. In this paper, we tackle this problem using a novel network architecture using multi scale feature fusion. Our network uses two different blocks, first which uses different filter sizes for convolution and merges all the individual feature maps. The second block uses dilated convolutions in place of fully connected layers thus reducing computations and increasing the receptive field. We present a new loss function for training the network which uses a depth regression term, SSIM loss term and a multinomial logistic loss term combined. We train and test our network on Make 3D dataset, NYU Depth V2 dataset and Kitti dataset using standard evaluation metrics for depth estimation comprised of RMSE loss and SILog loss. Our network outperforms previous state of the art methods with lesser parameters.