Factored Time-Lapse Video

ACM Transactions on Graphics (Proc. SIGGRAPH), August 2007

Kalyan Sunkavalli, Wojciech Matusik,
Hanspeter Pfister, Szymon Rusinkiewicz


(a) Original	(b) Reconstructed, no shadows	(c) Sun illumination only	(d) modified reflectance

We decompose a time-lapse sequence of photographs (a) into sun, sky, shadow, and reflectance components. The representation permits re-rendering without shadows (b) and without skylight (c), or modifying the reflectance of surfaces in the scene (d).

We describe a method for converting time-lapse photography captured with outdoor cameras into Factored Time-Lapse Video (FTLV): a video in which time appears to move faster (i.e., lapsing) and where data at each pixel has been factored into shadow, illumination, and reflectance components. The factorization allows a user to easily relight the scene, recover a portion of the scene geometry (normals), and to perform advanced image editing operations. Our method is easy to implement, robust, and provides a compact representation with good reconstruction characteristics. We show results using several publicly available time-lapse sequences.

PDF file

Quicktime file (13 MB, 4:09)

Kalyan Sunkavalli, Wojciech Matusik, Hanspeter Pfister, and Szymon Rusinkiewicz.
"Factored Time-Lapse Video."
ACM Transactions on Graphics (Proc. SIGGRAPH) 26(3), August 2007.

@article{Sunkavalli:2007:FTV,
   author = "Kalyan Sunkavalli and Wojciech Matusik and Hanspeter Pfister and Szymon
      Rusinkiewicz",
   title = "Factored Time-Lapse Video",
   journal = "ACM Transactions on Graphics (Proc. SIGGRAPH)",
   year = "2007",
   month = aug,
   volume = "26",
   number = "3"
}