A Hierarchical Architecture for Neural Materials
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910420166508544 |
|---|---|
| author | Xue, Bowen Zhao, Shuang Jensen, Henrik Wann Montazeri, Zahra |
| author_facet | Xue, Bowen Zhao, Shuang Jensen, Henrik Wann Montazeri, Zahra |
| contents | Neural reflectance models are capable of reproducing the spatially-varying appearance of many real-world materials at different scales. Unfortunately, existing techniques such as NeuMIP have difficulties handling materials with strong shadowing effects or detailed specular highlights. In this paper, we introduce a neural appearance model that offers a new level of accuracy. Central to our model is an inception-based core network structure that captures material appearances at multiple scales using parallel-operating kernels and ensures multi-stage features through specialized convolution layers. Furthermore, we encode the inputs into frequency space, introduce a gradient-based loss, and employ it adaptive to the progress of the learning phase. We demonstrate the effectiveness of our method using a variety of synthetic and real examples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_10135 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A Hierarchical Architecture for Neural Materials Xue, Bowen Zhao, Shuang Jensen, Henrik Wann Montazeri, Zahra Graphics Computer Vision and Pattern Recognition Neural reflectance models are capable of reproducing the spatially-varying appearance of many real-world materials at different scales. Unfortunately, existing techniques such as NeuMIP have difficulties handling materials with strong shadowing effects or detailed specular highlights. In this paper, we introduce a neural appearance model that offers a new level of accuracy. Central to our model is an inception-based core network structure that captures material appearances at multiple scales using parallel-operating kernels and ensures multi-stage features through specialized convolution layers. Furthermore, we encode the inputs into frequency space, introduce a gradient-based loss, and employ it adaptive to the progress of the learning phase. We demonstrate the effectiveness of our method using a variety of synthetic and real examples. |
| title | A Hierarchical Architecture for Neural Materials |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2307.10135 |