Self-Supervised Spatial And Zero-Shot Angular Super-Resolution by Spatial-Angular Implicit Representation For Rotating-View SNR-Efficient Diffusion MRI

2026-05-04 · Yinzhe Wu, Hongyu Rui, Fanwen Wang, Jiahao Huang, Zi Wang, Guang Yang arxiv

Rotating-view thick-slice acquisition is highly SNR-efficient for mesoscale diffusion MRI (dMRI) but requires numerous rotating views to satisfy Nyquist sampling, resulting in long scan time. We propose a self-supervised Spatial-Angular Implicit Neural Representation (SA-INR) that reconstructs high-resolution dMRI from a single view per diffusion direction, representing a massive acceleration. Our model, an MLP conditioned on a b=0 structural prior and the b-direction via FiLM, is trained end-to-end on the anisotropic input. The framework not only accurately reconstructs the trained b-directions (spatial SR) but also learns a continuous q-space representation, enabling high-fidelity "zero-shot" synthesis of unseen b-directions (angular SR). On simulated data, our method achieved high fidelity for both trained (34.82 dB) and unseen (33.08 dB) directions. Most importantly, the synthesized angular data also improved the quantitative accuracy of downstream DTI model fitting. Our SA-INR framework breaks the classical sampling limits, paving the way for fast, quantitative high-resolution dMRI.

📄 PDF Abstract BibTeX arXiv:2605.02575

Code (0)

등록된 구현이 없습니다.

SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers

2021-12-17 · Lin Liu, Shanxin Yuan, Jianzhuang Liu, Xin Guo 외

We propose a novel zero-shot multi-frame image restoration method for removing unwanted obstruction elements (such as rains, snow, and moire patterns) that vary in successive frames. It has three stages: transformer pre-…

Denoising Image Restoration Rain Removal

FM-RME: Foundation Model Empowered Radio Map Estimation

2026-02-15 · Dong Yang, Yue Wang, Songyang Zhang, Yingshu Li 외 arxiv

Traditional radio map estimation (RME) techniques fail to capture multi-dimensional and dynamic characteristics of complex spectrum environments. Recent data-driven methods achieve accurate RME in spatial domain, but ign…

Zero-shot Generalization

SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation

2021-08-27 · ICCV 2021 10 · Jiaxin Cheng, Soumyaroop Nandi, Prem Natarajan, Wael Abd-Almageed

Unlike conventional zero-shot classification, zero-shot semantic segmentation predicts a class label at the pixel level instead of the image level. When solving zero-shot semantic segmentation problems, the need for pixe…

Knowledge Distillation Segmentation Semantic Segmentation zero-shot-classification+2

TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Image Denoising

2026-04-06 · Junyoung Park, Youngjin Oh, Nam Ik Cho arxiv

Blind-spot networks (BSNs) enable self-supervised image denoising by preventing access to the target pixel, allowing clean signal estimation without ground-truth supervision. However, this approach assumes pixel-wise noi…

Knowledge Distillation Image Denoising

Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models

2021-09-10 · EMNLP 2021 11 · Tassilo Klein, Moin Nabi

Can we get existing language models and refine them for zero-shot commonsense reasoning? This paper presents an initial study exploring the feasibility of zero-shot commonsense reasoning for the Winograd Schema Challenge…

Language Modeling Language Modelling Self-Supervised Learning