NOIR: Neural Operator mapping for Implicit Representations
2026-03-13 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors introduce NOIR, a system that approaches medical imaging by treating images as continuous functions rather than fixed grids of pixels. Instead of using traditional methods that work on fixed image resolution, NOIR learns transformations between these continuous representations, allowing it to work well at different resolutions. They tested NOIR on various tasks like segmenting images and completing shapes on several medical datasets, finding it performs competitively and handles new image resolutions robustly. Their work suggests new ways to process medical images beyond standard pixel-based deep learning.
medical imagingimplicit neural representationsneural operatorsfunction spacesimage segmentationimage synthesisimage-to-image translationshape completiondeep learningresolution independence
Authors
Sidaty El Hadramy, Nazim Haouchine, Michael Wehrli, Philippe C. Cattin
Abstract
This paper presents NOIR, a framework that reframes core medical imaging tasks as operator learning between continuous function spaces, challenging the prevailing paradigm of discrete grid-based deep learning. Instead of operating on fixed pixel or voxel grids, NOIR embeds discrete medical signals into shared Implicit Neural Representations and learns a Neural Operator that maps between their latent modulations, enabling resolution-independent function-to-function transformations. We evaluate NOIR across multiple 2D and 3D downstream tasks, including segmentation, shape completion, image-to-image translation, and image synthesis, on several public datasets such as Shenzhen, OASIS-4, SkullBreak, fastMRI, as well as an in-house clinical dataset. It achieves competitive performance at native resolution while demonstrating strong robustness to unseen discretizations, and empirically satisfies key theoretical properties of neural operators. The project page is available here: https://github.com/Sidaty1/NOIR-io.