Proceedings Article10.1109/ICCE.2015.7066365
An automatic depth map generation method by image classification
Hao Dong,Shouyi Yin,Guangli Jiang,Leibo Liu,Shaojun Wei +4 more
- 26 Mar 2015
- pp 168-169
3
TL;DR: An automatic algorithm is presented which generates depth map for 2D to 3D conversion by fusing global depth gradient and local depth refinement by using warm/cool color theory.
read more
Abstract: This paper presents an automatic algorithm which generates depth map for 2D to 3D conversion. The depth map is generated by fusing global depth gradient and local depth refinement. First, the proposed algorithm judges the scene type of the input image. Then, it generates global depth gradient of the image according to its scene type. At last, local depth refinement is implemented by using warm/cool color theory. Experimental results show that the algorithm has advantages in both adaptability and processing time.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Depth information extraction method based on image classification
Jin Xin,Li Qian,Dai Qionghai +2 more
- 01 Jun 2016
TL;DR: In this paper, the authors proposed a depth information extraction method based on image classification, which comprises the following steps that: 1) the type of an image is detected, and whether the image is one of four types of a long-view image, a left-view, a right-view and a common image is judged, and then depth assignment is performed on the segmented different blocks according to the horizontal coordinates.
4
Reconfigurable VLSI Architecture for Real-Time 2D-to-3D Conversion
TL;DR: A data reuse method to reduce memory traffic for the proposed architecture so that the overall performance is improved to realize real-time conversion of 2-D-to-3-D conversion.
3
DCF: Disparity computing framework for stereo vision systems
TL;DR: In this article , the main components of a stereo vision system are integrated to promote disparity map construction, which can be applied to different applications, such as benchmarking proposals, computer and robotic applications, triangulation, and 3D reconstruction.
1
References
Use of the Hough transformation to detect lines and curves in pictures
Richard O. Duda,Peter E. Hart +1 more
TL;DR: It is pointed out that the use of angle-radius rather than slope-intercept parameters simplifies the computation further, and how the method can be used for more general curve fitting.
Depth-image-based rendering (DIBR), compression, and transmission for a new approach on 3D-TV
TL;DR: Details of a system that allows for an evolutionary introduction of depth perception into the existing 2D digital TV framework are presented and a comparison with the classical approach of "stereoscopic" video is compared.
1.6K
Depth map generation by image classification
TL;DR: A novel and fully automatic technique to estimate depth information from a single input image, based on a new image classification technique able to classify digital images as indoor, outdoor with geometric elements or outdoor without geometric elements.
171
A real-time 1080p 2D-to-3D video conversion system
Sung-Fang Tsai,Chao-Chung Cheng,Chung-Te Li,Liang-Gee Chen +3 more
- 22 Jul 2011
TL;DR: A 2D-to-3D video conversion system capable of real-time 1920×1080p conversion and combining the global depth gradient and local depth refinement, generated 3D images have comfortable and vivid quality, and algorithm has very low computational complexity.
64
Creating Depth Map from 2D Scene Classification
Yea-Shuan Huang,Fang-Hsuan Cheng,Yun-Hui Liang +2 more
- 18 Jun 2008
TL;DR: This paper proposes a method that generates the depth map of a single image based on scene classification, which works well and produces good stereoscopic effect.
20