mlsanityData to 7 Oct 2026

Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANs

arXiv 2103.16938 ↗First posted 31 Mar 2021cs.CV cs.LG eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

Real-time estimation of actual environment depth is an essential module for various autonomous system tasks such as localization, obstacle detection and pose estimation. During the last decade of machine learning, extensive deployment of deep learning methods to computer vision tasks yielded successful approaches for realistic depth synthesis out of a simple RGB modality. While most of these models rest on paired depth data or availability of video sequences and stereo images, there is a lack of methods facing single-image depth synthesis in an unsupervised manner. Therefore, in this study, latest advancements in the field of generative neural networks are leveraged to fully unsupervised single-image depth synthesis. To be more exact, two cycle-consistent generators for RGB-to-depth and depth-to-RGB transfer are implemented and simultaneously optimized using the Wasserstein-1 distance. To ensure plausibility of the proposed method, we apply the models to a self acquised industrial data set as well as to the renown NYU Depth v2 data set, which allows comparison with existing approaches. The observed success in this study suggests high potential for unpaired single-image depth estimation in real world applications.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 45 references that are in the map. First posted on arXiv 31 Mar 2021.

Builds on

26 of 45 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  5. 2017Improved Training of Wasserstein GANscited by 2,223
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  7. 2018Group Normalizationcited by 1,514
  8. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  9. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  10. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  11. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  12. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
14 more
  1. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  2. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  3. 2019Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentationcited by 258
  4. 2019FastDepth: Fast Monocular Depth Estimation on Embedded Systemscited by 93
  5. 2017Deep learning for undersampled MRI reconstructioncited by 91
  6. 2017SfM-Net: Learning of Structure and Motion from Videocited by 89
  7. 2020Monocular Depth Estimation Based On Deep Learning: An Overviewcited by 68
  8. 2019Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimationcited by 61
  9. 2018AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimationcited by 54
  10. 2018Unsupervised Adversarial Depth Estimation using Cycled Generative Networkscited by 45
  11. 2018Cross-modality image synthesis from unpaired data using CycleGAN: Effects of gradient consistency loss and training data sizecited by 42
  12. 2019Monocular Depth Estimation: A Surveycited by 37
  13. 2017Learning to solve inverse problems using Wasserstein losscited by 11
  14. 2019Projection-Based 2.5D U-net Architecture for Fast Volumetric Segmentationcited by 6

Built on by

Not cited yet.