Fast MRF Optimization with Application to Depth Reconstruction
Authors:
- Qifeng ChenQCQifeng Chen
- Vladlen KoltunVKVladlen Koltun
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 12 (10636919) , 3914-3921
Abstract
We describe a simple and fast algorithm for optimizing Markov random fields over images. The algorithm performs block coordinate descent by optimally updating a horizontal or vertical line in each step. While the algorithm is not as accurate as state-of-the-art MRF solvers on traditional benchmark problems, it is trivially parallelizable and produces competitive results in a fraction of a second. As an application, we develop an approach to increasing the accuracy of consumer depth cameras. The presented algorithm enables high-resolution MRF optimization at multiple frames per second and substantially increases the accuracy of the produced range images.Keywords
This publication has 22 references indexed in Scilit:
- Enhanced Computer Vision With Microsoft Kinect Sensor: A ReviewIEEE Transactions on Cybernetics, 2013
- Layer Depth Denoising and Completion for Structured-Light RGB-D Cameras2013
- A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems2013
- Coherent Spatiotemporal Filtering, Upsampling and Rendering of RGBZ VideosComputer Graphics Forum, 2012
- Accuracy and Resolution of Kinect Depth Data for Indoor Mapping ApplicationsSensors, 2012
- Estimation of Intrinsic Image Sequences from Image+Depth Video2012
- Fusion of range and color images for denoising and resolution enhancement with a non-local filterComputer Vision and Image Understanding, 2010
- Fast, Approximately Optimal Solutions for Single and Dynamic MRFs2007
- Efficient Belief Propagation for Early VisionInternational Journal of Computer Vision, 2006
- Colorization using optimizationACM Transactions on Graphics, 2004