TY - GEN
T1 - Depth prediction from a single image with conditional adversarial networks
AU - Jung, Hyungjoo
AU - Kim, Youngjung
AU - Min, Dongbo
AU - Oh, Changjae
AU - Sohn, Kwanghoon
N1 - Funding Information:
This work was supported by Institute for Information and communications Technology Promotion (IITP) grant funded by the Korea government (MSIP) (No. R0115-16-1007, High quality 2d-to-multiview contents generation from large-scale RGB+D database).
Publisher Copyright:
© 2017 IEEE.
PY - 2018/2/20
Y1 - 2018/2/20
N2 - 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.
AB - 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.
KW - Deep neural network
KW - Depth from a single image
KW - Generative adversarial learning
KW - RGB-D database
UR - http://www.scopus.com/inward/record.url?scp=85045295216&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2017.8296575
DO - 10.1109/ICIP.2017.8296575
M3 - Conference contribution
AN - SCOPUS:85045295216
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1717
EP - 1721
BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PB - IEEE Computer Society
T2 - 24th IEEE International Conference on Image Processing, ICIP 2017
Y2 - 17 September 2017 through 20 September 2017
ER -