An Interactive Perspective Scene Completion Framework Guided by Complanate Mesh = An Interactive Perspective Scene Completion Framework Guided by Complanate Mesh

다국어 초록 (Multilingual Abstract)

This paper presents an efficient interactive framework for perspective scene completion and editing tasks, which are available largely in the real world but rarely studied in the field of image completion. Considering that it is quite hard to extract perspective information from a single image, this work starts from a friendly and portable interactive platform to obtain the basic perspective data. Then, in order to make this interface less sensitive, easier and more flexible, a perspective-rectification based correction mechanism is proposed to iteratively update the locations of the initial points selected by users. At last, a complanate mesh is generated by the geometry calculations from these corrected initial positions. This mesh must approximate the perspective direction and the structure topology as much as possible so that the filling process can be conducted under the constraint of the perspective effects of the original image. Our experiments show the results with good qualities and performances, and also demonstrate the validity of our approaches by various perspective scenes and images.

참고문헌 (Reference)

1 A. Schödl, "Video textures" 489-498, 2000

2 J. -B. Huang, "Transformation Guided Image Completion" 1-9, 2013

3 C. Barnes, "The generalized patchmatch correspondence algorithm" 29-43, 2010

4 A. A. Efros, "Texture synthesis by non-parametric sampling" 1033-1038, 1999

5 M. Ashikhmin, "Synthesizing natural textures" 217-226, 2001

6 K. He, "Statistics of patch offsets for image completion" 16-29, 2012

7 Y. Wexler, "Space-time completion of video" 29 (29): 463-476, 2007

8 M. Bertalmio, "Simultaneous structure and texture image inpainting" 12 (12): 882-889, 2003

9 J. Hays, "Scene completion using millions of photographs" 26 (26): 1-7, 2007

10 A. Criminisi, "Region filling and object removal by exemplar-based image inpainting" 13 (13): 1200-1212, 2004

11 L. Liang, "Real-time texture synthesis by patch-based sampling" 20 (20): 127-150, 2001

12 P. Pérez, "Poisson image editing" 313-318, 2003

13 C. Barnes, "Patchmatch : a randomized correspondence algorithm for structural image editing" 28 (28): 1-11, 2009

14 Z. Zhou, "Non-stationary texture synthesis by adversarial expansion" 37 (37): 1-13, 2018

15 Y. Liu, "Near-regular texture analysis and manipulation" 23 (23): 368-376, 2004

16 Y. D. Chen, "Live accurate and dense reconstruction from a handheld camera" 24 (24): 387-397, 2013

17 D. Pavić, "Interactive image completion with perspective correction" 22 (22): 671-681, 2006

18 A. Agarwala, "Interactive digital photomontage" 23 (23): 294-302, 2004

19 A. A. Efros, "Image quilting for texture synthesis and transfer" 341-346, 2001

20 S. Darabi, "Image melding : combining inconsistent images using patch-based synthesis" 31 (31): 1-10, 2012

21 M. Bertalmio, "Image inpainting" 417-424, 2000

22 J. Sun, "Image completion with structure propagation" 24 (24): 861-868, 2005

23 J. -B. Huang, "Image Completion Using Planar Structure Guidance" 33 (33): 1-10, 2016

24 M. Wilczkowiak, "Hole filling through photomontage" 492-501, 2005

25 V. Kwatra, "Graphcut textures : image and video synthesis using graph cuts" 22 (22): 277-286, 2003

26 S. Lizuka, "Globally and Locally Consistent Image Completion" 36 (36): 1-14, 2017

27 I. Drori, "Fragment-based image completion" 22 (22): 303-312, 2003

28 L. -Y. Wei, "Fast texture synthesis using tree-structured vector quantization" 479-488, 2000

29 G. F. Zhang, "Consistent depth maps recovery from a video sequence" 1 (1): 974-988, 2009