# Enhanced Encoder-Decoder Architecture for Accurate Monocular Depth Estimation

arXiv: https://arxiv.org/abs/2410.11610 · HTML: https://mlsanity.com/paper/2410.11610/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 58 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation](https://mlsanity.com/paper/2307.14460/) (2023)
- [BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation](https://mlsanity.com/paper/2204.00987/) (2022)
- [High Quality Monocular Depth Estimation via Transfer Learning](https://mlsanity.com/paper/1812.11941/) (2018)
- [Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation](https://mlsanity.com/paper/1803.11029/) (2018)
- [Lightweight Monocular Depth Estimation through Guided Decoding](https://mlsanity.com/paper/2203.04206/) (2022)
- [Edit Temporal-Consistent Videos with Image Diffusion Model](https://mlsanity.com/paper/2308.09091/) (2023)
- [Joint Self-supervised Depth and Optical Flow Estimation towards Dynamic Objects](https://mlsanity.com/paper/2310.00011/) (2023)
- [Self-supervised Monocular Depth Estimation on Water Scenes via Specular Reflection Prior](https://mlsanity.com/paper/2404.07176/) (2024)
- [SGANVO: Unsupervised Deep Visual Odometry and Depth Estimation with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1906.08889/) (2019)
- [Depth Super-Resolution from Explicit and Implicit High-Frequency Features](https://mlsanity.com/paper/2303.09307/) (2023)

## Abstract (arXiv)

Estimating depth from a single 2D image is a challenging task due to the lack of stereo or multi-view data, which are typically required for depth perception. In state-of-the-art architectures, the main challenge is to efficiently capture complex objects and fine-grained details, which are often difficult to predict. This paper introduces a novel deep learning-based approach using an enhanced encoder-decoder architecture, where the Inception-ResNet-v2 model serves as the encoder. This is the first instance of utilizing Inception-ResNet-v2 as an encoder for monocular depth estimation, demonstrating improved performance over previous models. It incorporates multi-scale feature extraction to enhance depth prediction accuracy across various object sizes and distances. We propose a composite loss function comprising depth loss, gradient edge loss, and Structural Similarity Index Measure (SSIM) loss, with fine-tuned weights to optimize the weighted sum, ensuring a balance across different aspects of depth estimation. Experimental results on the KITTI dataset show that our model achieves a significantly faster inference time of 0.019 seconds, outperforming vision transformers in efficiency while maintaining good accuracy. On the NYU Depth V2 dataset, the model establishes state-of-the-art performance, with an Absolute Relative Error (ARE) of 0.064, a Root Mean Square Error (RMSE) of 0.228, and an accuracy of 89.3% for δ < 1.25. These metrics demonstrate that our model can accurately and efficiently predict depth even in challenging scenarios, providing a practical solution for real-time applications.