paper-with-me

홈 › Papers

Flip Distribution Alignment VAE for Multi-Phase MRI Synthesis

2025-10-03 · Xiaoyan Kui, Qianmu Xiao, Qqinsong Li, Zexin Ji, JIelin Zhang, Beiji Zou arxiv

Separating shared and independent features is crucial for multi-phase contrast-enhanced (CE) MRI synthesis. However, existing methods use deep autoencoder generators with low parameter efficiency and lack interpretable training strategies. In this paper, we propose Flip Distribution Alignment Variational Autoencoder (FDA-VAE), a lightweight feature-decoupled VAE model for multi-phase CE MRI synthesis. Our method encodes input and target images into two latent distributions that are symmetric concerning a standard normal distribution, effectively separating shared and independent features. The Y-shaped bidirectional training strategy further enhances the interpretability of feature separation. Experimental results show that compared to existing deep autoencoder-based end-to-end synthesis methods, FDA-VAE significantly reduces model parameters and inference time while effectively improving synthesis quality. The source code is publicly available at https://github.com/QianMuXiao/FDA-VAE.

📄 PDF Abstract BibTeX arXiv:2510.02970

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis

2023-06-30 · ICCV 2023 1 · Seunghyeon Seo, Yeonjin Chang, Nojun Kwak

Neural Radiance Field (NeRF) has been a mainstream in novel view synthesis with its remarkable quality of rendered images and simple architecture. Although NeRF has been developed in various directions improving continuo…

3D geometryDepth EstimationNeRFNovel View Synthesis

When Human Preferences Flip: An Instance-Dependent Robust Loss for RLHF

2025-11-30 · Yifan Xu, Xichen Ye, Yifan Chen, Qiaosheng Zhang arxiv

Quality of datasets plays an important role in large language model (LLM) alignment. In collecting human feedback, however, preference flipping is ubiquitous and causes corruption in data annotation; the issue necessitat…

Reinforcement Learning

Unlearnable phases of matter

2026-02-11 · Tarun Advaith Kumar, Yijian Zou, Amir-Reza Negari, Roger G. Melko 외 arxiv

We identify fundamental limitations in machine learning by demonstrating that non-trivial mixed-state phases of matter are computationally hard to learn. Focusing on unsupervised learning of distributions, we show that a…

DeepPhase: Periodic Autoencoders for Learning Motion Phase Manifolds

2022-07-22 · ACM Transactions on Graphics 2022 7 · Sebastian Starke, Ian Mason, Taku Komura

Learning the spatial-temporal structure of body movements is a fundamental problem for character motion synthesis. In this work, we propose a novel neural network architecture called the Periodic Autoencoder that can lea…

Motion Synthesis

DCGANs for Realistic Breast Mass Augmentation in X-ray Mammography

2019-09-04 · Basel Alyafi, Oliver Diaz, Robert Marti

Early detection of breast cancer has a major contribution to curability, and using mammographic images, this can be achieved non-invasively. Supervised deep learning, the dominant CADe tool currently, has played a great …

Lesion Detectionobject-detectionObject Detection