Deep Manifold Prior
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.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingGaussian ProcessesSimilar Papers 제목 키워드 기반
Variational Autoencoder with Learned Latent Structure
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
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 NetworkExploiting Manifold Structured Data Priors for Improved MR Fingerprinting Reconstruction
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…
GPUEncoded Prior Sliced Wasserstein AutoEncoder for learning latent manifold representations
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
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