Perceptual depth estimation from a single 2d image based on visual perception theory

Authors:
Li Bing;Xu De;Feng Songhe;Wu Aimin;Yang Xu
Affiliations:
Institute of Computer Science, Beijing Jiaotong University, Beijing, China;Institute of Computer Science, Beijing Jiaotong University, Beijing, China;Institute of Computer Science, Beijing Jiaotong University, Beijing, China;Institute of Computer Science, Beijing Jiaotong University, Beijing, China;Institute of Computer Science, Beijing Jiaotong University, Beijing, China
Venue:
PCM'06 Proceedings of the 7th Pacific Rim conference on Advances in Multimedia Information Processing
Year:
2006

Citing 7
Cited 0

Depth from focus

Pattern Recognition Letters
A Generalized Depth Estimation Algorithm with a Single Image

IEEE Transactions on Pattern Analysis and Machine Intelligence
Reconstruction of Linearly Parameterized Models from Single Images with a Camera of Unknown Focal Length

IEEE Transactions on Pattern Analysis and Machine Intelligence
Depth Estimation from Image Structure

IEEE Transactions on Pattern Analysis and Machine Intelligence
Depth Estimation and Image Restoration Using Defocused Stereo Pairs

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Geometric Approach to Shape from Defocus

IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimating face-pose consistency based on synthetic view space

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Quantified Score

Hi-index	0.01

Visualization

Abstract

The depth of image is conventionally defined as the distance between the corresponding scene point of the image and the pinhole of the camera, which is not harmony with the depth perception of human vision. In this paper we define a new perceptual depth of image which is perceived by human vision. The traditional computation models of image depth are all based on the physical imaging model, which ignore the human depth perception. This paper presents a novel computation model based on the visual perception theory. In this approach, we can get the relative perceptual depth from a single 2-D image. Experimental results show that our model is effective and corresponds to the human perception.