Depth prediction from a single image with conditional adversarial networks

Hyungjoo Jung, Youngjung Kim, Dongbo Min, Changjae Oh, Kwanghoon SohnICIP 2017 · OpenReview

Abstract

Recent works on machine learning have greatly advanced the accuracy of depth estimation from a single image. However, resulting depth images are still visually unsatisfactory, often producing poor boundary localization and spurious regions. In this paper, we formulate this problem from single images as a deep adversarial learning framework. A two-stage convolutional network is designed as a generator to sequentially predict global and local structures of the depth image. At the heart of our approach is a training criterion based on adversarial discriminator which attempts to distinguish between real and generated depth images as accurately as possible. Our model enables more realistic and structure-preserving depth prediction from a single image, compared to state-of-the-arts approaches. An experimental comparison demonstrates the effectiveness of our approach on large RGB-D dataset.
BibTeX
@inproceedings{jung2017depth,
  author = {Hyungjoo Jung and Youngjung Kim and Dongbo Min and Changjae Oh and Kwanghoon Sohn},
  title = {{Depth prediction from a single image with conditional adversarial networks}},
  booktitle = {ICIP},
  year = {2017},
  url = {https://openreview.net/forum?id=CrqGzcVgMG},
}

Loading related content...

Figure