# Deep Neural Networks for Accurate Depth Estimation with Latent Space Features

arXiv: https://arxiv.org/abs/2502.11777 · HTML: https://mlsanity.com/paper/2502.11777/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 39 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 9 of 9)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [Tightly Coupled 3D Lidar Inertial Odometry and Mapping](https://mlsanity.com/paper/1904.06993/) (2019)
- [Unsupervised Monocular Depth Estimation in Highly Complex Environments](https://mlsanity.com/paper/2107.13137/) (2021)
- [Learning Latent Vector Spaces for Product Search](https://mlsanity.com/paper/1608.07253/) (2016)
- [Unsupervised Odometry and Depth Learning for Endoscopic Capsule Robots](https://mlsanity.com/paper/1803.01047/) (2018)
- [Reinforcement Learning in Topology-based Representation for Human Body Movement with Whole Arm Manipulation](https://mlsanity.com/paper/1809.04322/) (2018)

## Abstract (arXiv)

Depth estimation plays a pivotal role in advancing human-robot interactions, especially in indoor environments where accurate 3D scene reconstruction is essential for tasks like navigation and object handling. Monocular depth estimation, which relies on a single RGB camera, offers a more affordable solution compared to traditional methods that use stereo cameras or LiDAR. However, despite recent progress, many monocular approaches struggle with accurately defining depth boundaries, leading to less precise reconstructions. In response to these challenges, this study introduces a novel depth estimation framework that leverages latent space features within a deep convolutional neural network to enhance the precision of monocular depth maps. The proposed model features dual encoder-decoder architecture, enabling both color-to-depth and depth-to-depth transformations. This structure allows for refined depth estimation through latent space encoding. To further improve the accuracy of depth boundaries and local features, a new loss function is introduced. This function combines latent loss with gradient loss, helping the model maintain the integrity of depth boundaries. The framework is thoroughly tested using the NYU Depth V2 dataset, where it sets a new benchmark, particularly excelling in complex indoor scenarios. The results clearly show that this approach effectively reduces depth ambiguities and blurring, making it a promising solution for applications in human-robot interaction and 3D scene reconstruction.