Deep monocular depth estimation via integration of global and local predictions
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 …
depth estimation. However, the resulting depth images are still over-smoothed and …
3D-TV content creation: automatic 2D-to-3D video conversion
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 …
rollout of 3D-TV will require a backward-compatible transmission/distribution system …
Three-dimensional video postproduction and processing
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 …
processing as well as an outlook to remaining challenges and opportunities. First …
Stereo/multiview picture quality: Overview and recent advances
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 …
issues. For the percept of depth to be convincing, consistent, and comfortable, a large …
Semi-automatic 2D-to-3D conversion using disparity propagation
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 …
especially for dynamic scenes. In this paper, a novel semi-automatic 2D-to-3D conversion …
Depth estimation based on global motion
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 …
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 …
dimensional (2D) displays do, the depth information required for 3D displays is unavailable …
Depth prediction from a single image with conditional adversarial networks
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 …
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
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 …
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 …
6, 2009. The present application for patent is related to the follow ing co-pending US patent …