# Pruning AMR: Efficient Visualization of Implicit Neural Representations via Weight Matrix Analysis

arXiv: https://arxiv.org/abs/2512.02967 · HTML: https://mlsanity.com/paper/2512.02967/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 29 references that are in the map.
- First posted on arXiv 2 Dec 2025.

## Builds on (most cited first, 11 of 11)

- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018)
- [Provable Filter Pruning for Efficient Neural Networks](https://mlsanity.com/paper/1911.07412/) (2019)
- [Data-Independent Neural Pruning via Coresets](https://mlsanity.com/paper/1907.04018/) (2019)
- [Adaptively Placed Multi-Grid Scene Representation Networks for Large-Scale Data Visualization](https://mlsanity.com/paper/2308.02494/) (2023)
- [Model Preserving Compression for Neural Networks](https://mlsanity.com/paper/2108.00065/) (2021)
- [Learning robust marking policies for adaptive mesh refinement](https://mlsanity.com/paper/2207.06339/) (2022)
- [Distributed Stochastic Optimization of a Neural Representation Network for Time-Space Tomography Reconstruction](https://mlsanity.com/paper/2404.19075/) (2024)

## Built on by (most cited first, 1 of 1)

- [A Query-Efficient Stochastic Volume Rendering Framework for Time-Varying Implicit Neural Volumes](https://mlsanity.com/paper/2607.28047/) (2026)

## Abstract (arXiv)

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.