Technical Papers

Color & Compositing

Monday, 22 July 9:00 AM - 10:30 AM
Session Chair: Alexander Hornung, Disney Research Zürich

User-Assisted Image Compositing for Photographic Lighting

A new approach that assists photographers to compose images of static scenes, viewed under dynamic lighting. The approach introduces a set of basis lights that combine several of the input images and provides controls to achieve effects photographers typically need; for example, accentuating the color or edges of objects.

Ivaylo Boyadzhiev
Cornell University

Sylvain Paris
Adobe Research

Kavita Bala
Cornell University

Probabilistic Color-by-Numbers: Suggesting Pattern Colorizations Using Factor Graphs

A probabilistic factor graph model for automatically coloring patterns. The model is trained on example patterns and can be sampled to generate diverse colorings for a target pattern. Results are demonstrated on a variety of coloring tasks. In a study, participants preferred sampled colorings to other automatic baselines.

Sharon Lin
Stanford University

Daniel Ritchie
Stanford University

Matthew Fisher
Stanford University

Pat Hanrahan
Stanford University

Optimizing Color Consistency in Photo Collections

A new method for automatically ensuring color consistency in typical real-world personal photo albums. Consistency may be induced without any user input, and user-specified edits of one or more photographs are automatically propagated to other photographs that share the same content.

Yoav HaCohen
The Hebrew University of Jerusalem

Eli Shechtman
Adobe Research

Dan Goldman
Adobe Systems Incorporated

Dani Lischinski
The Hebrew University of Jerusalem

Example-Based Video Color Grading

Color palettes of production movies are often adjusted by skilled colorists through a color-grading process that is difficult for amateurs to reproduce. This paper addresses this problem with an an example-based method. It solves temporal inconsistencies with a novel differential-geometry-based scheme akin to curvature flow.

Nicolas Bonneel
Harvard University

Kalyan Sunkavalli
Adobe Systems Incorporated

Sylvain Paris
Adobe Systems Incorporated

Hanspeter Pfister
Harvard University