Edge-aware Filtering and Joint Filtering
Nonlinear signal/image filtering is an important and fundamental component for many computer vision and graphics applications, which often require decomposing an image into a piecewise smooth base layer and a detail layer. The base layer captures the main structural information, while the detail layer contains the residual smaller scale details in the image. These layered signals can be manipulated and/or recombined in various ways to match different application goals. Over the last few decades, several edge-preserving filtering techniques have been proposed, stemming from different theories and principles. Thanks to their success in achieving high-quality smoothing results and significant computational advantages, these methods have found a great variety of applications.
We have developed several image filtering techniques, which achieve the substantial improvements in terms of both runtime efficiency and smoothing quality. Some of representative papers can be found below.
- J. Lu, K. Shi, D. Min, L. Lin, and M. N. Do, “Cross-Based Local Multipoint Filtering,” IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR), Jun. 2012. [code][readme]
- D. Min, J. Lu, and M. N. Do, “Depth Video Enhancement Based on Weighted Mode Filtering,” IEEE Trans. on Image Processing (TIP), vol. 21, no. 3, pp. 1176-1190, Mar. 2012. [code][readme]
- D. Min, S. Choi, J. Lu, B. Ham, K. Sohn, and M. N. Do, “Fast Global Image Smoothing Based on Weighted Least Squares,” IEEE Trans. on Image Processing (TIP), vol. 23, no. 12, pp. 5638-5653, Dec. 2014. [web][video]
- Our related work: Y. Li, D. Min, M. N. Do, and J. Lu, “Fast Guided Global Interpolation for Depth and Motion,” European Conf. Computer Vision (ECCV), Amsterdam, The Netherlands, Oct. 2016. (Spotlight) [pdf][supplementary][slides (PDF)][slides (PPT)][Matlab code]
For more information, please visit our website for a half-day tutorial in ICIP 2013.