EN
Structure-Texture Decomposition of RGB-D Images
Abstract
In this paper, we study the problem of separating texture from structure in RGB-D images. Our structure preserving image smoothing operator is based on the region covariance smoothing (RCS) method in [16] that we present a number of modifications to this framework to make it depth-aware and increase its effectiveness. In particular, we propose to incorporate three geometric depth features, namely height above ground, angle with gravity and horizontal disparity to the pool of image features used in that study. We also suggest to use a new kernel function based on KL-divergence between the distributions of extracted features. We demonstrate our approach on challenges images from NYU-Depth v2 Dataset [24], achieving more accurate decompositions than the state-of-the-art approaches which do not utilize any depth information.
Keywords
Kaynakça
- B. Arbelot, R. Vergne, T. Hurtut, and J. Thollot, “Automatic texture guided color transfer and colorization”, in Proc. Expresive'16, 2016
- J.-F. Aujol, G. Gilboa, T. Chan, and S. Osher, “Structure-texture image decomposition–modeling, algorithms, and parameter selection”, International Journal of Computer Vision, vol. 67, issue 1, Apr. 2006, pp. 111–136.
- A. Buades, B. Coll, and J.-M. Morel, “A non-local algorithm for image denoising”, in Proc. CVPR’05, vol. 2, 2005, pp. 60–65.
- M. Camplani, S. Hannuna, M. Mirmehdi, D. Damen, A. Paiement, L. Tao, and T. Burghardt, “Real-time RGB-D tracking with depth scaling kernelised correlation filters and occlusion handling”, in Proc. BMVC’15, 2015.
- H. Cho, Hyunjoon Lee, H. Kang, and S. Lee, “Bilateral texture filtering”, ACM Transactions on Graphics (TOG) – Proc. of ACM SIGGRAPH 2014, vol. 33, issue 4, July 2014.
- Z. Deng, S. Todorovic, and L.J. Latecki, “Semantic Segmentation of RGBD Images with Mutex Constraints”, in Proc. ICCV’15, 2015.
- K. Desingh, K.M. Krishna, D. Rajan, and C. Jawahar, “Depth really matters: Improving visual salient region detection with depth”, in Proc. BMVC’13, 2013.
- P. Dollar, and C. L. Zitnick, “Structured Forests for Fast Edge Detection”, in Proc. ICCV'13, 2013.
Ayrıntılar
Birincil Dil
İngilizce
Konular
-
Bölüm
-
Yazarlar
Yayımlanma Tarihi
6 Aralık 2016
Gönderilme Tarihi
24 Ağustos 2016
Kabul Tarihi
-
Yayımlandığı Sayı
Yıl 2016 Cilt: 4 Sayı: 4
APA
Erdem, A. (2016). Structure-Texture Decomposition of RGB-D Images. International Journal of Intelligent Systems and Applications in Engineering, 4(4), 111-118. https://izlik.org/JA88ZU73CD
AMA
1.Erdem A. Structure-Texture Decomposition of RGB-D Images. International Journal of Intelligent Systems and Applications in Engineering. 2016;4(4):111-118. https://izlik.org/JA88ZU73CD
Chicago
Erdem, Aykut. 2016. “Structure-Texture Decomposition of RGB-D Images”. International Journal of Intelligent Systems and Applications in Engineering 4 (4): 111-18. https://izlik.org/JA88ZU73CD.
EndNote
Erdem A (01 Aralık 2016) Structure-Texture Decomposition of RGB-D Images. International Journal of Intelligent Systems and Applications in Engineering 4 4 111–118.
IEEE
[1]A. Erdem, “Structure-Texture Decomposition of RGB-D Images”, International Journal of Intelligent Systems and Applications in Engineering, c. 4, sy 4, ss. 111–118, Ara. 2016, [çevrimiçi]. Erişim adresi: https://izlik.org/JA88ZU73CD
ISNAD
Erdem, Aykut. “Structure-Texture Decomposition of RGB-D Images”. International Journal of Intelligent Systems and Applications in Engineering 4/4 (01 Aralık 2016): 111-118. https://izlik.org/JA88ZU73CD.
JAMA
1.Erdem A. Structure-Texture Decomposition of RGB-D Images. International Journal of Intelligent Systems and Applications in Engineering. 2016;4:111–118.
MLA
Erdem, Aykut. “Structure-Texture Decomposition of RGB-D Images”. International Journal of Intelligent Systems and Applications in Engineering, c. 4, sy 4, Aralık 2016, ss. 111-8, https://izlik.org/JA88ZU73CD.
Vancouver
1.Aykut Erdem. Structure-Texture Decomposition of RGB-D Images. International Journal of Intelligent Systems and Applications in Engineering [Internet]. 01 Aralık 2016;4(4):111-8. Erişim adresi: https://izlik.org/JA88ZU73CD