Skip to yearly menu bar Skip to main content


Virtual presentation / poster accept

Interactive Portrait Harmonization

Jeya Maria Jose Valanarasu · HE Zhang · Jianming Zhang · Yilin Wang · Zhe Lin · Jose Echevarria · Yinglan Ma · Zijun Wei · Kalyan Sunkavalli · Vishal Patel

Keywords: [ low-level vision ] [ Image Editing ] [ harmonization ]


Abstract:

Current image harmonization methods consider the entire background as the guidance for harmonization. However, this may limit the capability for user to choose any specific object/person in the background to guide the harmonization. To enable flexible interaction between user and harmonization, we introduce interactive harmonization, a new setting where the harmonization is performed with respect to a selected region in the reference image instead of the entire background. A new flexible framework that allows users to pick certain regions of the background image and use it to guide the harmonization is proposed. Inspired by professional portrait harmonization users, we also introduce a new luminance matching loss to optimally match the color/luminance conditions between the composite foreground and select reference region. This framework provides more control to the image harmonization pipeline achieving visually pleasing portrait edits. Furthermore, we also introduce a new dataset carefully curated for validating portrait harmonization. Extensive experiments on both synthetic and real-world datasets show that the proposed approach is efficient and robust compared to previous harmonization baselines, especially for portraits.

Chat is not available.