Dense Correspondences across Scenes

This topic aims to establish dense correspondences between challenging image pairs in presence of significant variance in geometric and photometric transformation (e.g. scale, rotation, wide baseline, large and non-rigid motions, illumination changes, image quality) and also across different scene contents.

H. Yang, W.-Y. Lin, and J. Lu, “Daisy Filter Flow: A Generalized Discrete Approach to Dense Correspondences,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, Jun. 2014. [pdf][web]

Our related work:
- J. Lu, H. Yang, D. Min, and M. N. Do, “PatchMatch Filter: Efficient Edge-Aware Filtering Meets Randomized Search for Fast Correspondence Field Estimation,” IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR), Jun. 2013. (Oral) [pdf][ppt]
- 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]

For more information, please visit our website for a half-day tutorial in ICME 2015.