Intrinsic Image Decompositions

This page lists the decompositions for all 5230 photos, using this algorithm:

Sean Bell, Kavita Bala, Noah Snavely. "Intrinsic Images in the Wild". ACM Transactions on Graphics (SIGGRAPH 2014). http://intrinsic.cs.cornell.edu.

and these parameters:

abs reflectance weight: 0
abs shading gray point: 0.5
abs shading weight: 500.0
chromaticity weight: 0
kmeans intensity scale: 0.5
kmeans n clusters: 20
n iters: 25
pairwise intensity chromaticity: True
pairwise weight: 10⁴
shading blur init method: none
shading blur sigma: 0.1
shading target norm: L2
shading target weight: 20000.0
split clusters: True
theta c: 0.025
theta l: 0.1
theta p: 0.1

View all algorithms.

Image

Reflectance

Shading

WHDR: 33.4% (δ: 0.1), Runtime: 200.3 s, Num. judgements: 84. View human reflectance judgements.

Image

Reflectance

Shading

WHDR: 34.7% (δ: 0.1), Runtime: 232.0 s, Num. judgements: 84. View human reflectance judgements.

Image

Reflectance

Shading

WHDR: 39.7% (δ: 0.1), Runtime: 301.3 s, Num. judgements: 84. View human reflectance judgements.

Image

Reflectance

Shading

WHDR: 46.5% (δ: 0.1), Runtime: 232.3 s, Num. judgements: 84. View human reflectance judgements.

Image

Reflectance

Shading

WHDR: 5.9% (δ: 0.1), Runtime: 104.3 s, Num. judgements: 85. View human reflectance judgements.

Image

Reflectance

Shading

WHDR: 8.5% (δ: 0.1), Runtime: 197.5 s, Num. judgements: 85. View human reflectance judgements.

Image

Reflectance

Shading

WHDR: 9.9% (δ: 0.1), Runtime: 218.4 s, Num. judgements: 85. View human reflectance judgements.

Image

Reflectance

Shading

WHDR: 10.0% (δ: 0.1), Runtime: 224.1 s, Num. judgements: 85. View human reflectance judgements.