Robust Semiautomatic 2D-to-3D Conversion with Welsch M-Estimator for Data Fidelity
Authors:
Open Access
- 4 April 2018
- journal article
- research article
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2018, 1-15
Abstract
Semiautomatic 2D-to-3D conversion plays an important role in generating 3D contents for display. However, most existing methods assume that user scribbles are perfectly correct, and only give acceptable results when user provides accurate labels. To address this problem, Welsch M-estimator data fidelity is used to resist erroneous scribbles. The Welsch M-estimator data fidelity which is able to alleviate the influence of inaccurate scribbles has theoretical guarantee by means of its redescending property. First, the Welsch M-estimator is introduced to measure the fidelity between estimated depth and user provided depth; then local smoothness is built by using color weighted Welsch M-estimator to make neighboring pixels with similar colors have similar depth values. Finally, we solve the problem using generalized iteratively reweighted least squares algorithm. Experiments demonstrate that our method obtains competitive performance in the absence of inaccurate scribbles and outperforms the state of the art both visually and quantitatively in the presence of inaccurate scribbles.Keywords
Funding Information
- Natural Science Foundation of Zhejiang Province (LY16F010014, LY18F020025, Y201533511, 61502256, 61671260, 2017A610109)
- Natural Science Foundation of Zhejiang Province (LY16F010014, LY18F020025, Y201533511, 61502256, 61671260, 2017A610109)
- Educational Commission of Zhejiang Province (LY16F010014, LY18F020025, Y201533511, 61502256, 61671260, 2017A610109)
- National Natural Science Foundation of China (LY16F010014, LY18F020025, Y201533511, 61502256, 61671260, 2017A610109)
- National Natural Science Foundation of China (LY16F010014, LY18F020025, Y201533511, 61502256, 61671260, 2017A610109)
- Natural Science Foundation of Ningbo Municipality (LY16F010014, LY18F020025, Y201533511, 61502256, 61671260, 2017A610109)
This publication has 30 references indexed in Scilit:
- Robust Low-Rank Tensor Recovery With Regularized Redescending M-EstimatorIEEE Transactions on Neural Networks and Learning Systems, 2015
- An MRF-Based Depth Upsampling: Upsample the Depth Map With Its Own PropertyIEEE Signal Processing Letters, 2015
- Toward Naturalistic 2D-to-3D ConversionIEEE Transactions on Image Processing, 2014
- Efficient Depth Propagation for Constructing a Layered Depth Image from a Single ImageComputer Graphics Forum, 2014
- Nonlocal Random Walks Algorithm for Semi-Automatic 2D-to-3D Image ConversionIEEE Signal Processing Letters, 2014
- Depth estimation for semi-automatic 2D to 3D conversion2012
- Coherent Spatiotemporal Filtering, Upsampling and Rendering of RGBZ VideosComputer Graphics Forum, 2012
- Convergence Analysis of Generalized Iteratively Reweighted Least Squares Algorithms on Convex Function SpacesSIAM Journal on Optimization, 2009
- "GrabCut"ACM Transactions on Graphics, 2004
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004