AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Fourier-Net: Fast Image Registration with Band-Limited Deformation

Xi Jia, Joseph Bartlett, Wei Chen, Siyang Song, Tianyang Zhang, Xinxing Cheng, Wenqi Lu, Zhaowen Qiu, Jinming Duan

AAAI 2023 · Architectures and efficiency › CNN design · approach: Dense matching and estimation CNNs · 41 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use band-limited Fourier-Net-S instead of TransMorph3D IXI registration · 3D IXIDice: .754±.124 -> .759±.132Improved
Use band-limited Fourier-Net-S instead of TransMorph3D IXI registration · 3D IXICPU inference time (s): 22.035 -> 1.919Improved
Use Fourier-Net-L instead of TransMorph-Large3D OASIS registration · 3D OASISHD95: 1.431 -> 1.375Improved
Increase band-limited patch size from 20×24 to 40×48 (ablation)Fourier-Net, 2D OASIS · 2D OASISDice: .735±.037 -> .756±.037Improved
Add the encoder DFT layer (ablation)Fourier-Net, 2D OASIS, patch 20×24 · 2D OASISDice: .664±.040 -> .732±.042Improved
Add the encoder DFT layer (ablation)Fourier-Net, 2D OASIS, patch 40×48 · 2D OASISDice: .675±.038 -> .756±.039Improved
Add squaring and scaling to the 20×24 Fourier-Net (ablation)Fourier-Net, 2D OASIS · 2D OASISnegative Jacobian percentage: .434±.355 -> 0.0±0.0Improved
Add squaring and scaling to the 40×48 Fourier-Net (ablation)Fourier-Net, 2D OASIS · 2D OASISnegative Jacobian percentage: .753±.407 -> <0.0001Improved
Add squaring and scaling to the 20×24 Fourier-Net (ablation)Fourier-Net, 2D OASIS · 2D OASISDice: .732±.042 -> .735±.037No clear effect
Add squaring and scaling to the 40×48 Fourier-Net (ablation)Fourier-Net, 2D OASIS · 2D OASISDice: .756±.039 -> .756±.037No clear effect
Increase Fourier-Net model size from small to large (ablation)Fourier-Net, 2D OASIS · 2D OASISDice: .748±.039 -> .759±.040Improved
Increase Fourier-Net model size from small to large (ablation)Fourier-Net, 2D OASIS · 2D OASISCPU inference time (s): .007 -> .037Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy