Unsupervised Single-shot Depth Estimation using Perceptual Reconstruction

TL;DR

This paper introduces an unsupervised single-shot depth estimation method using generative neural networks, leveraging perceptual reconstruction and novel optimization techniques, achieving higher accuracy across diverse datasets.

Contribution

It proposes a fully unsupervised approach with dual generators and a perceptual loss, advancing single-image depth estimation without requiring paired data or sequences.

Findings

Significant improvement in depth accuracy over state-of-the-art methods.

Effective across industrial, facial, and human body datasets.

Utilizes perceptual reconstruction for better depth synthesis.

Abstract

Real-time estimation of actual object depth is an essential module for various autonomous system tasks such as 3D reconstruction, scene understanding and condition assessment. During the last decade of machine learning, extensive deployment of deep learning methods to computer vision tasks has yielded approaches that succeed in achieving realistic depth synthesis out of a simple RGB modality. Most of these models are based on paired RGB-depth data and/or the availability of video sequences and stereo images. The lack of sequences, stereo data and RGB-depth pairs makes depth estimation a fully unsupervised single-image transfer problem that has barely been explored so far. This study builds on recent advances in the field of generative neural networks in order to establish fully unsupervised single-shot depth estimation. Two generators for RGB-to-depth and depth-to-RGB transfer are implemented and simultaneously optimized using the Wasserstein-1 distance, a novel perceptual reconstruction term and hand-crafted image filters. We comprehensively evaluate the models using industrial surface depth data as well as the Texas 3D Face Recognition Database, the CelebAMask-HQ database of human portraits and the SURREAL dataset that records body depth. For each evaluation dataset the proposed method shows a significant increase in depth accuracy compared to state-of-the-art single-image transfer methods.