Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.08161 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913961756065792 |
|---|---|
| author | Bokšanský, Jakub Meister, Daniel Benthin, Carsten |
| author_facet | Bokšanský, Jakub Meister, Daniel Benthin, Carsten |
| contents | The encoding of input parameters is one of the fundamental building blocks of neural network algorithms. Its goal is to map the input data to a higher-dimensional space, typically supported by trained feature vectors. The mapping is crucial for the efficiency and approximation quality of neural networks. We propose a novel geometry-aware encoding called GATE that stores feature vectors on the surface of triangular meshes. Our encoding is suitable for neural rendering-related algorithms, for example, neural radiance caching. It also avoids limitations of previous hash-based encoding schemes, such as hash collisions, selection of resolution versus scene size, and divergent memory access. Our approach decouples feature vector density from geometry density using mesh colors, while allowing for finer control over neural network training and adaptive level-of-detail. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_08161 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GATE: Geometry-Aware Trained Encoding Bokšanský, Jakub Meister, Daniel Benthin, Carsten Graphics The encoding of input parameters is one of the fundamental building blocks of neural network algorithms. Its goal is to map the input data to a higher-dimensional space, typically supported by trained feature vectors. The mapping is crucial for the efficiency and approximation quality of neural networks. We propose a novel geometry-aware encoding called GATE that stores feature vectors on the surface of triangular meshes. Our encoding is suitable for neural rendering-related algorithms, for example, neural radiance caching. It also avoids limitations of previous hash-based encoding schemes, such as hash collisions, selection of resolution versus scene size, and divergent memory access. Our approach decouples feature vector density from geometry density using mesh colors, while allowing for finer control over neural network training and adaptive level-of-detail. |
| title | GATE: Geometry-Aware Trained Encoding |
| topic | Graphics |
| url | https://arxiv.org/abs/2506.08161 |