Data-driven hallucination of different times of day from a single outdoor photo

  • Authors:
  • Yichang Shih;Sylvain Paris;Frédo Durand;William T. Freeman

  • Affiliations:
  • MIT CSAIL;Adobe;MIT CSAIL;MIT CSAIL

  • Venue:
  • ACM Transactions on Graphics (TOG)
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

We introduce "time hallucination": synthesizing a plausible image at a different time of day from an input image. This challenging task often requires dramatically altering the color appearance of the picture. In this paper, we introduce the first data-driven approach to automatically creating a plausible-looking photo that appears as though it were taken at a different time of day. The time of day is specified by a semantic time label, such as "night". Our approach relies on a database of time-lapse videos of various scenes. These videos provide rich information about the variations in color appearance of a scene throughout the day. Our method transfers the color appearance from videos with a similar scene as the input photo. We propose a locally affine model learned from the video for the transfer, allowing our model to synthesize new color data while retaining image details. We show that this model can hallucinate a wide range of different times of day. The model generates a large sparse linear system, which can be solved by off-the-shelf solvers. We validate our methods by synthesizing transforming photos of various outdoor scenes to four times of interest: daytime, the golden hour, the blue hour, and nighttime.