PatchNet
作者： Shi-Min Hu , Fang-Lue Zhang , Miao Wang , Ralph R. Martin , Jue Wang
关键词: Automatic image annotation 、 Computer science 、 Graph (abstract data type) 、 Dynamic imaging 、 Feature detection (computer vision) 、 Computer vision 、 Image representation 、 Artificial intelligence 、 Image editing 、 Image texture 、 Image processing
摘要: We introduce PatchNets, a compact, hierarchical representation describing structural and appearance characteristics of image regions, for use in editing. In PatchNet, an region with coherent is summarized by graph node, associated single representative patch, while geometric relationships between different regions are encoded labelled edges giving contextual information. The structure PatchNet allows coarse-to-fine description the image. show how this can be used as basis interactive, library-driven, user draws rough sketches to quickly specify editing constraints target system then automatically queries library find semantically-compatible candidate meet goal. Contextual matching performed using representation, allowing suitable found applied few seconds, even from containing thousands images.
acm.org
sci-hub.se 参考文章(65)
Stephen Gould, Yuhang Zhang, None, PatchMatchGraph: Building a Graph of Dense Patch Correspondences for Label Transfer Computer Vision – ECCV 2012. pp. 439- 452 ,(2012) , 10.1007/978-3-642-33715-4_32
Ce Liu, Jenny Yuen, Antonio Torralba, Josef Sivic, William T. Freeman, SIFT Flow: Dense Correspondence across Different Scenes Lecture Notes in Computer Science. pp. 28- 42 ,(2008) , 10.1007/978-3-540-88690-7_3
Vivek Kwatra, Greg Turk, Li-Yi Wei, Sylvain Lefebvre, State of the Art in Example-based Texture Synthesis eurographics. pp. 93- 117 ,(2009) , 10.2312/EGST.20091063
Aude Oliva, Antonio Torralba, Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope International Journal of Computer Vision. ,vol. 42, pp. 145- 175 ,(2001) , 10.1023/A:1011139631724
Olga Russakovsky, Yuanqing Lin, Kai Yu, Li Fei-Fei, Object-Centric Spatial Pooling for Image Classification Computer Vision – ECCV 2012. pp. 1- 15 ,(2012) , 10.1007/978-3-642-33709-3_1
Connelly Barnes, Eli Shechtman, Dan B. Goldman, Adam Finkelstein, The generalized patchmatch correspondence algorithm european conference on computer vision. pp. 29- 43 ,(2010) , 10.1007/978-3-642-15558-1_3
Adel Hlaoui, Shengrui Wang, A New Algorithm for Graph Matching with Application to Content-Based Image Retrieval Lecture Notes in Computer Science. pp. 291- 300 ,(2002) , 10.1007/3-540-70659-3_30
F. Chevalier, J.-P. Domenger, J. Benois-Pineau, M. Delest, Retrieval of objects in video by similarity based on graph matching Pattern Recognition Letters. ,vol. 28, pp. 939- 949 ,(2007) , 10.1016/J.PATREC.2006.12.009
Soheil Darabi, Eli Shechtman, Connelly Barnes, Dan B. Goldman, Pradeep Sen, Image melding: combining inconsistent images using patch-based synthesis international conference on computer graphics and interactive techniques. ,vol. 31, pp. 82- ,(2012) , 10.1145/2185520.2185578
Gilad Freedman, Raanan Fattal, Image and video upscaling from local self-examples ACM Transactions on Graphics. ,vol. 30, pp. 1- 11 ,(2011) , 10.1145/1944846.1944852