Intrinsic colorization

Xiaopei Liu, Liang Wan, Yingge Qu, Tien-Tsin Wong, Stephen Lin, Chi-Sing Leung, Pheng-Ann Heng

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

63 Citations (Scopus)

Abstract

In this paper, we present an example-based colorization technique robust to illumination differences between grayscale target and color reference images. To achieve this goal, our method performs color transfer in an illumination-independent domain that is relatively free of shadows and highlights. It first recovers an illumination-independent intrinsic reflectance image of the target scene from multiple color references obtained by web search. The reference images from the web search may be taken from different vantage points, under different illumination conditions, and with different cameras. Grayscale versions of these reference images are then used in decomposing the grayscale target image into its intrinsic reflectance and illumination components. We transfer color from the color reflectance image to the grayscale reflectance image, and obtain the final result by relighting with the illumination component of the target image. We demonstrate via several examples that our method generates results with excellent color consistency. © 2008 ACM.
Original languageEnglish
Title of host publicationACM SIGGRAPH Asia 2008 Papers, SIGGRAPH Asia'08
Publication statusPublished - 2008
EventACM SIGGRAPH Asia 2008 (SIGGRAPH Asia '08) - , Singapore
Duration: 10 Dec 200813 Dec 2008

Conference

ConferenceACM SIGGRAPH Asia 2008 (SIGGRAPH Asia '08)
Country/TerritorySingapore
Period10/12/0813/12/08

Research Keywords

  • Colorization
  • Intrinsic images

Fingerprint

Dive into the research topics of 'Intrinsic colorization'. Together they form a unique fingerprint.

Cite this