Deep monocular depth estimation via integration of global and local predictions

Y Kim, H Jung, D Min, K Sohn - IEEE transactions on Image …, 2018 - ieeexplore.ieee.org
Recent works on machine learning have greatly advanced the accuracy of single image
depth estimation. However, the resulting depth images are still over-smoothed and …

3D-TV content creation: automatic 2D-to-3D video conversion

L Zhang, C Vazquez, S Knorr - IEEE Transactions on …, 2011 - ieeexplore.ieee.org
Three-dimensional television (3D-TV) is the next major revolution in television. A successful
rollout of 3D-TV will require a backward-compatible transmission/distribution system …

Three-dimensional video postproduction and processing

A Smolic, P Kauff, S Knorr, A Hornung… - Proceedings of the …, 2011 - ieeexplore.ieee.org
This paper gives an overview of the state-of-the-art in 3-D video postproduction and
processing as well as an outlook to remaining challenges and opportunities. First …

Stereo/multiview picture quality: Overview and recent advances

S Winkler, D Min - Signal Processing: Image Communication, 2013 - Elsevier
Stereoscopic 3D content brings with it a variety of complex technological and perceptual
issues. For the percept of depth to be convincing, consistent, and comfortable, a large …

Semi-automatic 2D-to-3D conversion using disparity propagation

X Cao, Z Li, Q Dai - IEEE Transactions on Broadcasting, 2011 - ieeexplore.ieee.org
Estimating 3D information from an image sequence has long been a challenging problem,
especially for dynamic scenes. In this paper, a novel semi-automatic 2D-to-3D conversion …

Depth estimation based on global motion

R Zhang, Y Chen, M Karczewicz - US Patent 9,171,372, 2015 - Google Patents
BACKGROUND In recent years, technology (eg, televisions, dvd players, set top boxes, blu-
ray players, computers, and the like) has been developed to allow for 3D video …

A novel 2Dd-to-3D conversion system using edge information

CC Cheng, CT Li, LG Chen - IEEE Transactions on Consumer …, 2010 - ieeexplore.ieee.org
Although three-dimensional (3D) displays enhance visual quality more than two-
dimensional (2D) displays do, the depth information required for 3D displays is unavailable …

Depth prediction from a single image with conditional adversarial networks

H Jung, Y Kim, D Min, C Oh… - 2017 IEEE International …, 2017 - ieeexplore.ieee.org
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 …

Depth analogy: Data-driven approach for single image depth estimation using gradient samples

S Choi, D Min, B Ham, Y Kim, C Oh… - IEEE Transactions on …, 2015 - ieeexplore.ieee.org
Inferring scene depth from a single monocular image is a highly ill-posed problem in
computer vision. This paper presents a new gradient-domain approach, called depth …

Transforming video data in accordance with human visual system feedback metrics

VR Raveendran, JM Bauza, SS Soliman - US Patent 8,629,899, 2014 - Google Patents
This application claims the benefit of US Provisional Application No. 61/231.925, filed Aug.
6, 2009. The present application for patent is related to the follow ing co-pending US patent …