Presentation of SASNet @ CVPR 2026
We present our CVPR 2026 paper "SASNet: Spatially-Adaptive Sinusoidal Networks for INRs" at the IEEE/CVF Conference on Computer Vision and Pattern Recognition.
Jun 3, 2026
SASNet: Spatially-Adaptive Sinusoidal Networks for INRs
A spatially-adaptive sinusoidal network for implicit neural representations. A frozen frequency embedding fixes the frequency support while jointly learned spatial masks localize each neuron, giving sharper edges, less background noise, and faster convergence on images, volumes, and SDFs.
Jun 1, 2026
Structured Pruning in Implicit Neural Representations
Work in progress on structured pruning for implicit neural representations — removing whole sinusoidal neurons from a trained INR to shrink the model while preserving reconstruction quality.
Sep 15, 2024