DuFal: Dual-Frequency-Aware Learning for High-Fidelity Extremely Sparse-view CBCT Reconstruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915974839533568 |
|---|---|
| author | Van, Cuong Tran Pham, Trong-Thang Nguyen, Ngoc-Son Nguyen, Duy Minh Ho Le, Ngan |
| author_facet | Van, Cuong Tran Pham, Trong-Thang Nguyen, Ngoc-Son Nguyen, Duy Minh Ho Le, Ngan |
| contents | Sparse-view Cone-Beam Computed Tomography reconstruction from limited X-ray projections remains a challenging problem in medical imaging due to the inherent undersampling of fine-grained anatomical details, which correspond to high-frequency components. Conventional CNN-based methods often struggle to recover these fine structures, as they are typically biased toward learning low-frequency information. To address this challenge, this paper presents DuFal (Dual-Frequency-Aware Learning), a novel framework that integrates frequency-domain and spatial-domain processing via a dual-path architecture. The core innovation lies in our High-Local Factorized Fourier Neural Operator, which comprises two complementary branches: a Global High-Frequency Enhanced Fourier Neural Operator that captures global frequency patterns and a Local High-Frequency Enhanced Fourier Neural Operator that processes spatially partitioned patches to preserve spatial locality that might be lost in global frequency analysis. To improve efficiency, we design a Spectral-Channel Factorization scheme that reduces the Fourier Neural Operator parameter count. We also design a Cross-Attention Frequency Fusion module to integrate spatial and frequency features effectively. The fused features are then decoded through a Feature Decoder to produce projection representations, which are subsequently processed through an Intensity Field Decoding pipeline to reconstruct a final Computed Tomography volume. Experimental results on the LUNA16 and ToothFairy datasets demonstrate that DuFal significantly outperforms existing state-of-the-art methods in preserving high-frequency anatomical features, particularly under extremely sparse-view settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_15416 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DuFal: Dual-Frequency-Aware Learning for High-Fidelity Extremely Sparse-view CBCT Reconstruction Van, Cuong Tran Pham, Trong-Thang Nguyen, Ngoc-Son Nguyen, Duy Minh Ho Le, Ngan Computer Vision and Pattern Recognition Artificial Intelligence Sparse-view Cone-Beam Computed Tomography reconstruction from limited X-ray projections remains a challenging problem in medical imaging due to the inherent undersampling of fine-grained anatomical details, which correspond to high-frequency components. Conventional CNN-based methods often struggle to recover these fine structures, as they are typically biased toward learning low-frequency information. To address this challenge, this paper presents DuFal (Dual-Frequency-Aware Learning), a novel framework that integrates frequency-domain and spatial-domain processing via a dual-path architecture. The core innovation lies in our High-Local Factorized Fourier Neural Operator, which comprises two complementary branches: a Global High-Frequency Enhanced Fourier Neural Operator that captures global frequency patterns and a Local High-Frequency Enhanced Fourier Neural Operator that processes spatially partitioned patches to preserve spatial locality that might be lost in global frequency analysis. To improve efficiency, we design a Spectral-Channel Factorization scheme that reduces the Fourier Neural Operator parameter count. We also design a Cross-Attention Frequency Fusion module to integrate spatial and frequency features effectively. The fused features are then decoded through a Feature Decoder to produce projection representations, which are subsequently processed through an Intensity Field Decoding pipeline to reconstruct a final Computed Tomography volume. Experimental results on the LUNA16 and ToothFairy datasets demonstrate that DuFal significantly outperforms existing state-of-the-art methods in preserving high-frequency anatomical features, particularly under extremely sparse-view settings. |
| title | DuFal: Dual-Frequency-Aware Learning for High-Fidelity Extremely Sparse-view CBCT Reconstruction |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.15416 |