Stereo Computer Graphics

McAllister, David F.

doi:10.1007/978-1-4612-4306-9_8

Search citation statements

Order By: Relevance

Paper Sections

Select...

Previous Work1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2001

2023

Publication Types

Select...

Article2

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Acquisition Gonioreflectometers measure the reflectance, depending on the light and view direction [Erb80, WSB*98, LFTW06, McA02] but this process remains slow, as it requires the mechanical change of light and sensor position. For spherical objects, this process can be accelerated by imaging all normals at the same time [MWL*99].…”

Section: Previous Workmentioning

confidence: 99%

Learning to Learn and Sample BRDFs

Liu

Fischer

Ritschel

2023

Computer Graphics Forum

View full text Add to dashboard Cite

We propose a method to accelerate the joint process of physically acquiring and learning neural Bi‐directional Reflectance Distribution Function (BRDF) models. While BRDF learning alone can be accelerated by meta‐learning, acquisition remains slow as it relies on a mechanical process. We show that meta‐learning can be extended to optimize the physical sampling pattern, too. After our method has been meta‐trained for a set of fully‐sampled BRDFs, it is able to quickly train on new BRDFs with up to five orders of magnitude fewer physical acquisition samples at similar quality. Our approach also extends to other linear and non‐linear BRDF models, which we show in an extensive evaluation.

show abstract