24.0 Illumination and reflection🔗⧉

Contents of this part

• 24.1 Illumination related effects in a single image
  • 24.1.1 Intrinsic images: the unifying frame ($I = R\cdot S$)
  • 24.1.2 Multiple-light / spatially-varying white balance
  • 24.1.3 Reflection removal — pulling apart a transmission and a glass reflection
  • 24.1.4 Shadow detection and shadow removal
  • 24.1.5 Specular-highlight removal / "fake polarization" (the dichromatic model)
• 24.2 Mixed-lighting white balance
  • 24.2.1 Why a global gain must fail
  • 24.2.2 Estimating the per-pixel mixture: an under-determined inverse problem
  • 24.2.3 Correcting each region for its own light
  • 24.2.4 What came after
• 24.3 Dehazing
  • 24.3.1 Dehazing as a prior-driven inverse problem
  • 24.3.2 Differentiable image pipelines and algorithm optimization (Halide)
• 24.4 Intrinsic images with time lapse
  • 24.4.1 The split, and why one image can't do it
  • 24.4.2 Weiss 2001: the median of log-gradients
  • 24.4.3 Passive and controlled illumination
• 24.5 Colorization
  • 24.5.1 One channel in, three channels out
  • 24.5.2 A spectrum of priors: scribbles, references, and learned models
  • 24.5.3 The multimodality trap: why naïve colorization goes muddy
  • 24.5.4 Closing the loop: learned priors with a human's hints
  • 24.5.5 Plausible is not correct
  • 24.5.6 Where it sits

▸ full collapsible outline of this part