A Novel 2D-to-3D Conversion System Using Edge Information

A Novel 2D-to-3D Conversion System Using

Edge Information

IEEE Transactions on Consumer Electronics 2010Chao-Chung Cheng

Chung-Te liLiang-Gee Chen

IntroductionSome approaches that can generate 3D content

Time-of-flight depth sensorTriangular stereo vision3D graph rendering

IntroductionHow does our brain perceive depth?

Monocular cues： one of the major categories for depth perception

Motion parallax

Binocular cues

Monocular cuesInterposition (overlapping)

Relative Height

Familiar Size

Texture Gradient

Shadow

Linear Perspective

Proposed System

Block-Based Region GroupingDepth from Prior Hypothesis3D Image Visualization using Bilateral

Filtering and Depth Image-Based Rendering

Proposed 2D-to-3D Conversion System

Block-Based Region Grouping

1. Measure the similarity of neighboring blocks

2. The blocks are segmented into multiple groups by MST

Depth from Prior Hypothesis

1. Use a line detection algorithm[9] to detect the linear perspective of the scene

C.-C. Cheng, C.-T. Li, P.-S. Huang, T.-K. Lin, Y.-M. Tsai, and L.-G. Chen, “A block-based 2D-to-3D conversion system with bilateral filter,” in Proc. IEEE Int. Conf. Consumer Electronics, 2009

Depth from Prior Hypothesis

2. Find the corresponding depth map gradients

3. Compute the gravity center of the block group as the depth

3D Image Visualization using Bilateral Filtering and Depth Image-Based RenderingRemove the blocky artifacts by cross bilateral filter

Then the depth map is used to generate 3D image by DIBR[3]

W.-Y. Chen and Y.-L. Chang and S.-F. Lin and L.-F. Ding and L.-G. Chen, “Efficient depth image based rendering with edge dependent depth filter and interpolation,” in Proc. ICME, pp. 1314-1317, 2005

Experiment Result

Analysis of Computational ComplexityAnalysis of Visual Quality

Analysis of Computational Complexity

The computational complexity is Larger block size implies shorter computational

time but lower depth map quality

Analysis of Visual Quality

Analysis of Visual Quality

Analysis of Visual QualityComparing the depth quality and visual comfort

over 4 video data typesVideos that captured by a stereoscopic cameraProposed algorithmPrevious work of [9]Commercial software of DDD’s TriDef

Analysis of Visual Quality

ConclusionThe proposed algorithm uses edge information to

group the image into coherent regions.A simple depth hypothesis is determined by the

linear perspective of the scene.The algorithm is quality-scalable depending on the

block size.