paper-with-me

홈 › Papers

Deep Manifold Prior

2020-04-08 · Matheus Gadelha, Rui Wang, Subhransu Maji

We present a prior for manifold structured data, such as surfaces of 3D shapes, where deep neural networks are adopted to reconstruct a target shape using gradient descent starting from a random initialization. We show that surfaces generated this way are smooth, with limiting behavior characterized by Gaussian processes, and we mathematically derive such properties for fully-connected as well as convolutional networks. We demonstrate our method in a variety of manifold reconstruction applications, such as point cloud denoising and interpolation, achieving considerably better results against competitive baselines while requiring no training data. We also show that when training data is available, our method allows developing alternate parametrizations of surfaces under the framework of AtlasNet, leading to a compact network architecture and better reconstruction results on standard image to shape reconstruction benchmarks.

📄 PDF Abstract BibTeX arXiv:2004.04242

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingGaussian Processes

Similar Papers 제목 키워드 기반

Variational Autoencoder with Learned Latent Structure

2020-06-18 · Marissa C. Connor, Gregory H. Canal, Christopher J. Rozell

The manifold hypothesis states that high-dimensional data can be modeled as lying on or near a low-dimensional, nonlinear manifold. Variational Autoencoders (VAEs) approximate this manifold by learning mappings from low-…

MMCGAN: Generative Adversarial Network with Explicit Manifold Prior

2020-06-18 · Guanhua Zheng, Jitao Sang, Changsheng Xu

Generative Adversarial Network(GAN) provides a good generative framework to produce realistic samples, but suffers from two recognized issues as mode collapse and unstable training. In this work, we propose to employ exp…

Generative Adversarial Network

Exploiting Manifold Structured Data Priors for Improved MR Fingerprinting Reconstruction

2023-10-09 · Peng Li, Yuping Ji, Yue Hu

Estimating tissue parameter maps with high accuracy and precision from highly undersampled measurements presents one of the major challenges in MR fingerprinting (MRF). Many existing works project the recovered voxel fin…

GPU

Encoded Prior Sliced Wasserstein AutoEncoder for learning latent manifold representations

2020-10-02 · Sanjukta Krishnagopal, Jacob Bedrossian

While variational autoencoders have been successful in several tasks, the use of conventional priors are limited in their ability to encode the underlying structure of input data. We introduce an Encoded Prior Sliced Was…

PDD: Manifold-Prior Diverse Distillation for Medical Anomaly Detection

2026-03-07 · Xijun Lu, Hongying Liu, Fanhua Shang, Yanming Hui 외 arxiv

Medical image anomaly detection faces unique challenges due to subtle, heterogeneous anomalies embedded in complex anatomical structures. Through systematic Grad-CAM analysis, we reveal that discriminative activation map…

Anomaly Detection