Learning Neural Antiderivatives
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912599478632448 |
|---|---|
| author | Rubab, Fizza Nsampi, Ntumba Elie Balint, Martin Mujkanovic, Felix Seidel, Hans-Peter Ritschel, Tobias Leimkühler, Thomas |
| author_facet | Rubab, Fizza Nsampi, Ntumba Elie Balint, Martin Mujkanovic, Felix Seidel, Hans-Peter Ritschel, Tobias Leimkühler, Thomas |
| contents | Neural fields offer continuous, learnable representations that extend beyond traditional discrete formats in visual computing. We study the problem of learning neural representations of repeated antiderivatives directly from a function, a continuous analogue of summed-area tables. Although widely used in discrete domains, such cumulative schemes rely on grids, which prevents their applicability in continuous neural contexts. We introduce and analyze a range of neural methods for repeated integration, including both adaptations of prior work and novel designs. Our evaluation spans multiple input dimensionalities and integration orders, assessing both reconstruction quality and performance in downstream tasks such as filtering and rendering. These results enable integrating classical cumulative operators into modern neural systems and offer insights into learning tasks involving differential and integral operators. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17755 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Neural Antiderivatives Rubab, Fizza Nsampi, Ntumba Elie Balint, Martin Mujkanovic, Felix Seidel, Hans-Peter Ritschel, Tobias Leimkühler, Thomas Machine Learning Computer Vision and Pattern Recognition Graphics Neural fields offer continuous, learnable representations that extend beyond traditional discrete formats in visual computing. We study the problem of learning neural representations of repeated antiderivatives directly from a function, a continuous analogue of summed-area tables. Although widely used in discrete domains, such cumulative schemes rely on grids, which prevents their applicability in continuous neural contexts. We introduce and analyze a range of neural methods for repeated integration, including both adaptations of prior work and novel designs. Our evaluation spans multiple input dimensionalities and integration orders, assessing both reconstruction quality and performance in downstream tasks such as filtering and rendering. These results enable integrating classical cumulative operators into modern neural systems and offer insights into learning tasks involving differential and integral operators. |
| title | Learning Neural Antiderivatives |
| topic | Machine Learning Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2509.17755 |