eess.IVNov 11, 2026

Coarse-to-Fine 3D MRI Reconstruction via Resolution-Agnostic Neural Operators

Authors: Jiayun Wang, Ram Daftari, Weijie Gan, Valentin Duruisseaux, Ruibo Wang, Armeet Singh Jatyani, Boris Bonev, Anima Anandkumar

Organizations: Georgia Tech · Caltech · IIT Kanpur · Washington University in St. Louis · 

Abstract

Deep-learning-based 3D MRI reconstruction is limited in practice by the GPU memory and compute cost of full-volume training; 3D acquisitions are thus most often reconstructed by 2D models applied slice-by-slice and then stacked, which ignores through-plane (stacking-axis) structure. We reconstruct in full 3D and ask whether a model can be trained at low resolution (fast and memory-feasible) yet deployed at higher resolution. This coarse-to-fine strategy needs reliable cross-resolution performance, but standard networks are resolution-specific and degrade substantially when evaluated outside the training setting. We therefore use resolution-agnostic neural operators (NOs) and propose KIR-NO (k-space-to-Image Reconstruction Neural Operator), a discretization-agnostic framework for accelerated 3D MRI reconstruction. KIR-NO is trained with full backpropagation on low-resolution volumes and applied zero-shot to higher-resolution volumes at inference. Its core building block is a 3D neural operator based on discrete-continuous convolutions: convolutional filters are parameterized in a continuous basis and sampled at arbitrary voxel resolutions while preserving the local inductive bias of convolution. KIR-NO integrates these learned operators with physics-based consistency: a k-space neural-operator head first refines the undersampled Fourier measurements, and image-space neural-operator cascades then refine the reconstruction through interleaved data-consistency updates. Across 3D knee and brain MRI benchmarks, KIR-NO improves over classical and CNN baselines: it improves over a state-of-the-art 3D CNN by 2.2 dB PSNR at half resolution under 4x acceleration on SKM-TEA, with gains persisting at 8x and 16x. These results show that resolution-agnostic operators make coarse-to-fine 3D MRI reconstruction - cheap low-resolution training with high-resolution deployment - practical across anatomies.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. MK-ResRecon: Multi-Kernel Residual Framework for Texture-Aware 3D MRI Refinement from Sparse 2D Slices

    May 5, 2026Prajyot Pyati, Sapna Sachan, Amulya Kumar Mahto +13D Medical ImagingImage Reconstruction

  2. NOIR: Neural Operator mapping for Implicit Representations

    Mar 13, 2026Sidaty El Hadramy, Nazim Haouchine, Michael Wehrli +1Neural OperatorsMedical Image Synthesis

  3. One Evaluation, Any Operating Point: Hypernetwork-Amortized MeanFlow for 3D MRI Reconstruction

    Sep 15, 2026Ruibo WangAccelerated MRI ReconstructionMagnetic Resonance Imaging