Pruning AMR: Efficient Visualization of Implicit Neural Representations via Weight Matrix Analysis
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911298121367552 |
|---|---|
| author | Zvonek, Jennifer Gillette, Andrew |
| author_facet | Zvonek, Jennifer Gillette, Andrew |
| contents | An implicit neural representation (INR) is a neural network that approximates a spatiotemporal function. Many memory-intensive visualization tasks, including modern 4D CT scanning methods, represent data natively as INRs. While INRs are prized for being more memory-efficient than traditional data stored on a lattice, many visualization tasks still require discretization to a regular grid. We present PruningAMR, an algorithm that builds a mesh with resolution adapted to geometric features encoded by the INR. To identify these geometric features, we use an interpolative decomposition pruning method on the weight matrices of the INR. The resulting pruned network is used to guide adaptive mesh refinement, enabling automatic mesh generation tailored to the underlying resolution of the function. Starting from a pre-trained INR--without access to its training data--we produce a variable resolution visualization with substantial memory savings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02967 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pruning AMR: Efficient Visualization of Implicit Neural Representations via Weight Matrix Analysis Zvonek, Jennifer Gillette, Andrew Machine Learning Numerical Analysis An implicit neural representation (INR) is a neural network that approximates a spatiotemporal function. Many memory-intensive visualization tasks, including modern 4D CT scanning methods, represent data natively as INRs. While INRs are prized for being more memory-efficient than traditional data stored on a lattice, many visualization tasks still require discretization to a regular grid. We present PruningAMR, an algorithm that builds a mesh with resolution adapted to geometric features encoded by the INR. To identify these geometric features, we use an interpolative decomposition pruning method on the weight matrices of the INR. The resulting pruned network is used to guide adaptive mesh refinement, enabling automatic mesh generation tailored to the underlying resolution of the function. Starting from a pre-trained INR--without access to its training data--we produce a variable resolution visualization with substantial memory savings. |
| title | Pruning AMR: Efficient Visualization of Implicit Neural Representations via Weight Matrix Analysis |
| topic | Machine Learning Numerical Analysis |
| url | https://arxiv.org/abs/2512.02967 |