基于子帧缝合的老电影大面积破损修复

doi:10.12066/j.issn.1007-2861.2010

上海大学学报(自然科学版) ›› 2018, Vol. 24 ›› Issue (4): 503-511.doi: 10.12066/j.issn.1007-2861.2010

• 数字影视技术 • 下一篇

基于子帧缝合的老电影大面积破损修复

夏天然¹^,², 丁友东¹^,²(), 于冰¹^,², 黄曦¹^,²

1. 上海大学上海电影学院, 上海 200072
2. 上海大学上海电影特效工程技术研究中心, 上海 200072

收稿日期:2018-03-09 出版日期:2018-08-31 发布日期:2018-08-31
通讯作者: 丁友东 E-mail:ydding@shu.edu.cn
基金资助:
国家自然科学基金资助项目(61402278);上海市科委科技攻关资助项目(16511101302);上海大学电影学高峰学科和上海电影特效工程技术研究中心资助项目(16dz2251300)

An old film restoration method using subframe quilting

XIA Tianran¹^,², DING Youdong¹^,²(), YU Bing¹^,², HUANG Xi¹^,²

1. Shanghai Film Academy, Shanghai University, Shanghai 200072, China
2. Shanghai Engineering Research Center for Motion Picture Special Effects, Shanghai University, Shanghai 200072, China

Received:2018-03-09 Online:2018-08-31 Published:2018-08-31
Contact: DING Youdong E-mail:ydding@shu.edu.cn

摘要/Abstract

摘要：

相较于噪声、斑点和划痕, 大面积破损一直是老电影修复的一大难点. 考虑到老电影序列中包含丰富的前后帧信息, 提出一种基于子帧缝合的老电影帧画面修复方法. 首先, 在修复前对电影序列进行镜头分割和帧画面预处理, 在选定破损帧的前后参考帧后, 再根据破损帧的破损范围框选破损子帧和对应前后参考子帧; 然后, 将破损子帧作为黑帧处理, 通过前后参考子帧插值得出合适的中间子帧; 最后, 将得到的中间子帧缝合于原破损帧的破损区域, 进而完成老电影的大面积破损修复. 该方法针对性地解决了老电影存在的大面积破损问题, 亦可作为初步修复工具协助人工完成老电影大面积破损的半自动修复.

关键词: 老电影, 帧修复, 双向帧插值, 块匹配, 图像缝合

Abstract:

Unlike noise, spots and scratches, widespread damage is the major difficulty in old film restoration. Considering that old film sequences contain rich frame information, a subframe quilting method for widespread damage in old films is suggested here. Before repair, the first step is to segment lens and preprocess frame screen. After selecting the forward and backward reference frames, we now choose the damaged subframes and the corresponding reference subframes. Then, we interpolate the intermediate subframes according to two reference subframes. Finally, we quilt the intermediate subframe into the damaged area, and complete the widespread damage restoration. This method not only solves the problem of widespread damage, but also assists old film repairers with preliminary repair.

Key words: old films, frame completion, bidirectional frame interpolation, patch match, image quilting

中图分类号:

TP391.41

夏天然, 丁友东, 于冰, 黄曦. 基于子帧缝合的老电影大面积破损修复[J]. 上海大学学报(自然科学版), 2018, 24(4): 503-511.

XIA Tianran, DING Youdong, YU Bing, HUANG Xi. An old film restoration method using subframe quilting[J]. Journal of Shanghai University（Natural Science Edition）, 2018, 24(4): 503-511.

图/表 7

图1

图2

图3

表1

表2

图4

图5

参考文献 21

[1]	Simone C, Ozan A T, Nikolce S , et al. Advanced tools and framework for historical film restoration[J]. Journal of Electronic Imaging, 2017,26(1):11-21.
[2]	Zeng Y C, Lin S Y, Shih Y P , et al. Intensity flicker removal in digitized old films using global-local histogram transform[C] // Advances in Multimedia Information Processing-PCM 2009. 2009:45-54.
[3]	Umeda Y, Arakawa K . Removal of film scratches using exemplar-based inpainting with directional median filter[C] // International Symposium on Communications and Information Technologies (ISCIT). 2012: 6-11.
[4]	Yu B, Ding Y D, Huang X , et al. Corrupted old film sequences restoration using improved PatchMatch and low-rank matrix recovery[C] // International Conference on Audio, Language and Image Processing (ICALIP). 2017: 295-300.
[5]	Efros A A, Leung T K . Texture synthesis by non-parametric sampling[C] // The Proceedings of the Seventh IEEE International Conference on Computer Vision. 2002: 1033-1038.
[6]	Criminisi A, Perez P, Toyama K . Region filling and object removal by exemplar-based image inpainting[J]. IEEE Transactions on Image Processing, 2004,13(9):1200-1212. pmid: 15449582
[7]	Huang J B, Kang S B, Ahuja N , et al. Image completion using planar structure guidance[J]. ACM Transactions on Graphics, 2014,33(4):129.
[8]	Wexler Y, Shechtman E, Irani M . Space-time video completion[C] // Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2004: 120-127.
[9]	Cheung V, Frey B J, Jojic N . Video epitomes[C] // IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). 2005: 42-49.
[10]	Wexler Y, Shechtman E, Irani M . Space-time completion of video[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007,29(3):463-476. doi: 10.1109/TPAMI.2007.60 pmid: 17224616
[11]	于冰, 丁友东, 董荪 , 等. 基于分组鲁棒主成分分析的老电影修复[J]. 上海大学学报(自然科学版), 2017,23(3):315-323.
[12]	Newson A, Almansa A, Fradet M , et al. Video inpainting of complex scenes[J]. SIAM Journal on Imaging Sciences, 2015,7(4):1993-2019.
[13]	Newson A, Fradet M, Gousseau Y , et al. Towards fast, generic video inpainting [EB/OL]. [2018-05-23]. https://hal.archives-ouvertes.fr/hal-00838927/document.
[14]	黄曦, 丁友东, 吴兵 . 老电影全局闪烁修复系统的设计与实现[J]. 电视技术, 2016,40(12):125-129.
[15]	Liu C, Freeman W T, Adelson E H , et al. Human-assisted motion annotation [EB/OL]. [ 2018- 05- 23]. http://persci.mit.edu/pub_pdfs/Motion_CVPR08.pdf.
[16]	Barnes C, Shechtman E, Finkelstein A , et al. PatchMatch: a randomized correspondence algorithm for structural image editing [EB/OL]. [ 2018- 06- 09]. http://www.uni-forst.gwdg.de/$\sim $wkurth/scg_saalfeld_a.pdf.
[17]	Barnes C, Shechtman E, Goldman B , et al. The generalized PatchMatch correspondence algorithm [EB/OL]. [ 2018- 05- 23]. http://profs.scienze.univr.it/$\sim $swan/dwnld/EVS/63130029.pdf.
[18]	Pérez P, Gangnet M, Blake A . Poisson image editing[J]. ACM Transactions on Graphics, 2003,22(3):313-318.
[19]	Farbman Z, Hoffer G, Lipman Y , et al. Coordinates for instant image cloning[M]. ACM Siggraph, 2009: 341-352.
[20]	Efros A A, Freeman W T . Image quilting for texture synthesis and transfer[C] // Proceedings of the 28$^{\rm th}$ annual Conference on Computer Graphics and Interactive Techniques. 2001: 341-346.
[21]	Kwatra V, Schödl A, Essa I , et al. Graphcut textures: image and video synthesis using graph cuts [EB/OL]. [ 2018- 05- 23]. http://gamma.cs.unc.edu/kwatra/publications/gc-final-lowres.pdf.

基于子帧缝合的老电影大面积破损修复

An old film restoration method using subframe quilting

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 21

相关文章 3

编辑推荐

Metrics

本文评价

[1]	于冰1,2, 丁友东1,2, 董荪1,2, 黄曦1,2. 基于分组鲁棒主成分分析的老电影修复[J]. 上海大学学报(自然科学版), 2017, 23(3): 315-323.
[2]	黄东晋, 张倩, 吴冏, 丁友东. 基于角点及局部特征的饮料瓶识别方法[J]. 上海大学学报(自然科学版), 2011, 17(3): 238-242.
[3]	赵培栋1，韩军1，闵友钢2，蒋慧钧2. 基于多帧参考的分块视频闪烁消除算法[J]. 上海大学学报(自然科学版), 2010, 16(4): 342-348.