Saliency-based depth-of-field rendering with flash and non-flash pairs

Xiangze ZHANG, Weichen XUE, Zhe WANG, Bin SHENG, Lizhuang MA, Ping LI

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

Depth of Field is an important factor to synthesize realistic photography effects. In our paper, we discuss a new image-based approach that can synthesize DoF effects without user iterations. Our approach can produce the based saliency maps with realtime performance. In particular, there is not depth information needed to capture from cameras. The depth information is approximated by using saliency maps. In particular, we take advantages of the flash non-flash image pairs to refine the DoF synthesis quality. The focused regions can be segmented using GrabCut. The experimental results show that the our image based DoF synthesis can simulate high-quality DoF effects efficiently. Copyright © 2014 the Owner/Author.
Original languageEnglish
Title of host publicationProceedings VRCAI 2014: The 13th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry
Place of PublicationNew York
PublisherAssociation for Computing Machinery
Pages133-140
ISBN (Print)9781450332545
DOIs
Publication statusPublished - 2014

Fingerprint

Photography
Cameras

Citation

Zhang, X., Xue, W., Wang, Z., Sheng, B., Ma, L., & Li, P. (2014). Saliency-based depth-of-field rendering with flash and non-flash pairs. In Proceedings VRCAI 2014: The 13th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry (pp. 133-140). New York: Association for Computing Machinery.

Keywords

  • Constant timeDepth-of-Field
  • Global illumination
  • Image defocus
  • Matting
  • Radiosity
  • Saliency