SphereFlow:透過超球面上的幾何傳輸補全缺失模態
SphereFlow: Missing Modality Imputation via Geometric Transport on Hypersphere
SphereFlow 將各模態投影至共享超球面潛在空間,透過流匹配及幾何感知調整,根據已觀察模態合成缺失模態。在 BraTS 多模態 MRI 補全及 CT-MRI 轉換實驗中,SphereFlow 的生成保真度在所有設定下達到最先進水平;使用補全數據進行下游腦腫瘤分割,與完整模態基準的差距縮小約 80%。
Published on Nov 3
Authors:
,
,
,
,
,
,
,
Abstract
SphereFlow projects modalities onto a shared hypersphere to enable short-range cross-modal imputation via flow matching with geometry-aware noise and decoder modifications.
Missing modality imputation aims to synthesize unobserved modalities from observed ones. Existing methods treat each modality as living on its own latent manifold, forcing the generator to learn a long, unstructured jump between them. We present SphereFlow, which takes a fundamentally different view: by projecting all modalities into a shared hyperspherical latent space via a frozen self-supervised encoder, cross-modal imputation reduces to short-range geometric transport between nearby points on the sphere. Realizing this idea with flow matching, however, exposes two geometric conflicts: the standard Gaussian noise source is catastrophically mismatched with the unit-norm data manifold, and the linear interpolation path departs the sphere surface into a region where the decoder has no training signal. We resolve both with simple, geometry-aware modifications: replacing the noise source with the observed-modality latent so that the velocity field learns only the cross-modal displacement, and training the decoder with a time-weighted loss that extends its domain to the near-surface region traversed by the flow. We prove that this data-as-source formulation reduces the worst-case off-manifold deviation from a quantity that grows with the latent dimension to a small, dimension-independent bound governed by inter-modality similarity. Experiments on BraTS multi-modal MRI imputation and CT-MRI translation demonstrate state-of-the-art generation fidelity across all settings, while downstream brain tumor segmentation with our imputed data closes roughly eighty percent of the gap to the full-modality oracle. Code is available at https://github.com/WTHH031230/SphereFlow.
View arXiv page View PDF GitHub 1 Add to collection
Get this paper in your agent:
hf papers read 2611.04414
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 1
Image-to-Image • Updated about 1 hour ago • 1WTHH031230/SphereFlow
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.04414 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.04414 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co