Pruning AMR: Efficient Visualization of Implicit Neural Representations via Weight Matrix Analysis
This work addresses memory efficiency in visualization for domains like 4D CT scanning, though it is incremental as it builds on existing INR methods.
The paper tackles the problem of memory-intensive visualization tasks for implicit neural representations (INRs) by introducing PruningAMR, an algorithm that uses weight matrix analysis to generate adaptive meshes, resulting in substantial memory savings without access to training data.
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.