Deep Neural Networks for Accurate Depth Estimation with Latent Space Features

TL;DR

This paper presents a novel deep learning framework utilizing latent space features and a dual encoder-decoder architecture to significantly improve monocular depth estimation accuracy, especially in complex indoor environments.

Contribution

It introduces a new depth estimation model with a dual encoder-decoder structure and a combined loss function, advancing the precision of monocular depth maps over existing methods.

Findings

Sets a new benchmark on NYU Depth V2 dataset

Reduces depth ambiguities and boundary blurring

Enhances depth map accuracy in complex indoor scenes

Abstract

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.