1. Video Information & Settings
Newson's method [1] and Huang's method [2] are incorporated in the comparison. To provide a clear comparison, all the videos corresponding to [5] have been slowed down by a factor of 2.
1. Video Information & Settings
Newson's method [1] and Huang's method [2] are incorporated in the comparison.
To provide a clear comparison, all the videos corresponding to [5] have been slowed
down by a factor of 2.
2. Object Removal with Dynamic Backgrounds
View results online:
(These video files were compressed at relatively low quality levels.)
3. Object Removal with Challenging Camera Motions
View results online:
(These video files were compressed at relatively low quality levels.)
High-quality video files and other updated contents are provided
HERE. (Google Drive)
Reference
[1] A. Newson, A. Almansa, M. Fradet, Y. Gousseau, and P. P´erez, “Video
inpainting of complex scenes,” SIAM J. Imaging Sci., vol. 7, no. 4, pp.
1993–2019, 2014.
[2] J.-B. Huang, S. B. Kang, N. Ahuja, and J. Kopf, “Temporally coherent completion
of dynamic video,” ACM Trans. Graph., vol. 35, no. 6, pp. 196:1-196:11, 2016.
[3] R. P´eteri, S. Fazekas, and M. J. Huiskes, “DynTex: a comprehensive database of
dynamic textures,” Pattern Recognition Letters, vol. 31, no. 12, pp. 1627–1632, 2010.
[4] Y. Wang, P.-M. Jodoin, F. Porikli, J. Konrad, Y. Benezeth, and P. Ishwar, “CDnet 2014:
an expanded change detection benchmark dataset,” in Proc. IEEE Conf. Comput. Vis.
Pattern Recognit. Workshops, 2014, pp. 387–394.
[5] F. Perazzi, J. Pont-Tuset, B. McWilliams, L. Van Gool, M. Gross, and
A. Sorkine-Hornung, “A benchmark dataset and evaluation methodology for video object
segmentation,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 724–732.
