@CONFERENCE\{IMM2007-05482,
    author       = "L. Schj{\o}th and J. R. Frisvad and K. Erleben and J. Sporring",
    title        = "Photon Differentials",
    year         = "2007",
    month        = "dec",
    keywords     = "Ray tracing, global illumination, photon mapping, caustics, ray differentials",
    pages        = "179-186",
    booktitle    = "Proceedings of {GRAPHITE} 2007",
    volume       = "",
    series       = "",
    editor       = "",
    publisher    = "ACM",
    organization = "",
    address      = "",
    url          = "http://www2.compute.dtu.dk/pubdb/pubs/5482-full.html",
    abstract     = "A number of popular global illumination algorithms use density
estimation to approximate indirect illumination. The density estimate
is performed on finite points - particles - generated by a
stochastic sampling of the scene. In the course of the sampling,
particles, representing light, are stochastically emitted from the
light sources and reflected around the scene. The sampling induces
noise, which in turn is handled by the density estimate during the
illumination reconstruction. Unfortunately, this noise reduction imposes
a systematic error (bias), which is seen as a blurring of prominent
illumination features. This is often not desirable as these may
lose clarity or vanish altogether.

We present an accurate method for reconstruction of indirect illumination
with photon mapping. Instead of reconstructing illumination
using classic density estimation on finite points, we use the correlation
of light footprints, created by using Ray Differentials during
the light pass. This procedure gives a high illumination accuracy,
improving the trade-off between bias and variance considerable as
compared to traditional particle tracing algorithms. In this way we
preserve structures in indirect illumination.",
    isbn_issn    = "9781595939128"
}