Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2510.08394 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914306397831168 |
|---|---|
| author | Yaldiz, Mustafa B. Mehta, Ishit Raghavan, Nithin Meuleman, Andreas Li, Tzu-Mao Ramamoorthi, Ravi |
| author_facet | Yaldiz, Mustafa B. Mehta, Ishit Raghavan, Nithin Meuleman, Andreas Li, Tzu-Mao Ramamoorthi, Ravi |
| contents | Neural fields excel at representing continuous visual signals but typically operate at a single, fixed resolution. We present a simple yet powerful method to optimize neural fields that can be prefiltered in a single forward pass. Key innovations and features include: (1) We perform convolutional filtering in the input domain by analytically scaling Fourier feature embeddings with the filter's frequency response. (2) This closed-form modulation generalizes beyond Gaussian filtering and supports other parametric filters (Box and Lanczos) that are unseen at training time. (3) We train the neural field using single-sample Monte Carlo estimates of the filtered signal. Our method is fast during both training and inference, and imposes no additional constraints on the network architecture. We show quantitative and qualitative improvements over existing methods for neural-field filtering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08394 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Spectral Prefiltering of Neural Fields Yaldiz, Mustafa B. Mehta, Ishit Raghavan, Nithin Meuleman, Andreas Li, Tzu-Mao Ramamoorthi, Ravi Graphics Computer Vision and Pattern Recognition Neural fields excel at representing continuous visual signals but typically operate at a single, fixed resolution. We present a simple yet powerful method to optimize neural fields that can be prefiltered in a single forward pass. Key innovations and features include: (1) We perform convolutional filtering in the input domain by analytically scaling Fourier feature embeddings with the filter's frequency response. (2) This closed-form modulation generalizes beyond Gaussian filtering and supports other parametric filters (Box and Lanczos) that are unseen at training time. (3) We train the neural field using single-sample Monte Carlo estimates of the filtered signal. Our method is fast during both training and inference, and imposes no additional constraints on the network architecture. We show quantitative and qualitative improvements over existing methods for neural-field filtering. |
| title | Spectral Prefiltering of Neural Fields |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.08394 |