ACM Transactions on Graphics (Proc. SIGGRAPH) August 2013

Optimizing Color Consistency in Photo Collections

Yoav HaCohen Eli Shechtman Dan B Goldman Dani Lischinski
Hebrew University Adobe Systems Adobe Systems Hebrew University
Editing a photo collection with our method. First row: input images exhibiting inconsistent appearance. Red arrows indicate pairs of images that were detected to share content. Second row: automatically induced consistent appearance. Third row: after propagating user adjustment of the leftmost photo (photos with similar content are affected more strongly). Fourth row: propagation of an adjustment done to the sixth photo. Previous adjustment remains as constraint. (Note: adjustments are deliberately exaggerated in this example.)


With dozens or even hundreds of photos in today’s digital photo albums, editing an entire album can be a daunting task. Existing automatic tools operate on individual photos without ensuring consistency of appearance between photographs that share content. In this paper, we present a new method for consistent editing of photo collections. Our method automatically enforces consistent appearance of images that share content without any user input. When the user does make changes to selected images, these changes automatically propagate to other images in the collection, while still maintaining as much consistency as possible. This makes it possible to interactively adjust an entire photo album in a consistent manner by manipulating only a few images.

Our method operates by efficiently constructing a graph with edges linking photo pairs that share content. Consistent appearance of connected photos is achieved by globally optimizing a quadratic cost function over the entire graph, treating user-specified edits as constraints in the optimization. The optimization is fast enough to provide interactive visual feedback to the user. We demonstrate the usefulness of our approach using a number of personal and professional photo collections, as well as internet collections.