Learning to Learn and Sample BRDFs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913510663913472 |
|---|---|
| author | Liu, Chen Fischer, Michael Ritschel, Tobias |
| author_facet | Liu, Chen Fischer, Michael Ritschel, Tobias |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_03510 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Learning to Learn and Sample BRDFs Liu, Chen Fischer, Michael Ritschel, Tobias Graphics Computer Vision and Pattern Recognition 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. |
| title | Learning to Learn and Sample BRDFs |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2210.03510 |