61.3: Stereoscopic 3D Content Depth Tuning Guided by Human Visual Models

2011 ◽  
Vol 42 (1) ◽  
pp. 916-919 ◽  
Author(s):  
Chang Yuan ◽  
Hao Pan ◽  
Scott Daly
Keyword(s):  
Stereoscopic 3D ◽  
Visual Models ◽  
3D Content

Stereoscopic 3D

2013 ◽  
pp. 258-287
Author(s):  
Ian Barba ◽  
James Brewer ◽  
Brenda Swinford
Keyword(s):  
Background Information ◽  
Second Phase ◽  
Future Directions ◽  
3D Technology ◽  
Stereoscopic 3D ◽  
Related Research ◽  
Potential Benefits ◽  
Two Phases ◽  
Texas Tech University ◽  
3D Content

This chapter summarizes information gathered in the first two phases of research being conducted at Texas Tech University (TTU) Libraries on the feasibility and potential benefits of using stereoscopic 3D content in a classroom or library. The authors share background information gathered during the first phase of the research, including an overview of stereoscopic 3D technology and a review of related research. They then discuss findings and recommendations from the second phase of the research, including detailed coverage of 3D equipment, practical advice for using 3D technology, and results from demonstration and survey sessions conducted with TTU faculty, staff, and students. The authors also share options for accessing and creating stereoscopic 3D content. They end with a discussion of some future directions of stereoscopic 3D.

scholarly journals Semi-Automatic Depth Map Generation In Unconstrained Images And Video Sequences For 2D To Stereoscopic 3D Conversion

2021 ◽  
Author(s):  
Raymond Phan
Keyword(s):  
Random Walks ◽  
Human Perception ◽  
Depth Map ◽  
Graph Cuts ◽  
Depth Image ◽  
Video Sequences ◽  
Edge Preserving ◽  
Stereoscopic 3D ◽  
Depth Maps ◽  
3D Content

In this work, we describe a system for accurately estimating depth through synthetic depth maps in unconstrained conventional monocular images and video sequences, to semi-automatically convert these into their stereoscopic 3D counterparts. With current accepted industry efforts, this conversion process is performed automatically in a black box fashion, or manually converted using human operators to extract features and objects on a frame by frame basis, known as rotoscopers. Automatic conversion is the least labour intensive, but allows little to no user intervention, and error correction can be difficult. Manual is the most accurate, providing the most control, but very time consuming, and is prohibitive for use to all but the largest production studios. Noting the merits and disadvantages between these two methods, a semi-automatic method blends the two together, allowing for faster and accurate conversion, while decreasing time for releasing 3D content for user digest. Semi-automatic methods require the user to place user-defined strokes over the image, or over several keyframes in the case of video, corresponding to a rough estimate of the depths in the scene at these strokes. After, the rest of the depths are determined, creating depth maps to generate stereoscopic 3D content, and Depth Image Based Rendering is employed to generate the artificial views. Here, depth map estimation can be considered as a multi-label image segmentation problem: each class is a depth value. Additionally, for video, we allow the option of labeling only the first frame, and the strokes are propagated using one of two techniques: A modified computer vision object tracking algorithm, and edge-aware temporally consistent optical flow./p pFundamentally, this work combines the merits of two well-respected segmentation algorithms: Graph Cuts and Random Walks. The diffusion of depths, with smooth gradients from Random Walks, combined with the edge preserving properties from Graph Cuts can create the best possible result. To demonstrate that the proposed framework generates good quality stereoscopic content with minimal effort, we create results and compare to the current best known semi-automatic conversion framework. We also show that our results are more suitable for human perception in comparison to this framework.

scholarly journals Semi-Automatic Depth Map Generation In Unconstrained Images And Video Sequences For 2D To Stereoscopic 3D Conversion

2021 ◽  
Author(s):  
Raymond Phan
Keyword(s):  
Random Walks ◽  
Human Perception ◽  
Depth Map ◽  
Graph Cuts ◽  
Depth Image ◽  
Video Sequences ◽  
Edge Preserving ◽  
Stereoscopic 3D ◽  
Depth Maps ◽  
3D Content

In this work, we describe a system for accurately estimating depth through synthetic depth maps in unconstrained conventional monocular images and video sequences, to semi-automatically convert these into their stereoscopic 3D counterparts. With current accepted industry efforts, this conversion process is performed automatically in a black box fashion, or manually converted using human operators to extract features and objects on a frame by frame basis, known as rotoscopers. Automatic conversion is the least labour intensive, but allows little to no user intervention, and error correction can be difficult. Manual is the most accurate, providing the most control, but very time consuming, and is prohibitive for use to all but the largest production studios. Noting the merits and disadvantages between these two methods, a semi-automatic method blends the two together, allowing for faster and accurate conversion, while decreasing time for releasing 3D content for user digest. Semi-automatic methods require the user to place user-defined strokes over the image, or over several keyframes in the case of video, corresponding to a rough estimate of the depths in the scene at these strokes. After, the rest of the depths are determined, creating depth maps to generate stereoscopic 3D content, and Depth Image Based Rendering is employed to generate the artificial views. Here, depth map estimation can be considered as a multi-label image segmentation problem: each class is a depth value. Additionally, for video, we allow the option of labeling only the first frame, and the strokes are propagated using one of two techniques: A modified computer vision object tracking algorithm, and edge-aware temporally consistent optical flow./p pFundamentally, this work combines the merits of two well-respected segmentation algorithms: Graph Cuts and Random Walks. The diffusion of depths, with smooth gradients from Random Walks, combined with the edge preserving properties from Graph Cuts can create the best possible result. To demonstrate that the proposed framework generates good quality stereoscopic content with minimal effort, we create results and compare to the current best known semi-automatic conversion framework. We also show that our results are more suitable for human perception in comparison to this framework.

Sign in / Sign up

Export Citation Format

Share Document