paper-with-me

홈 › Papers

Super-resolution Variational Auto-Encoders

2020-06-09 · Ioannis Gatopoulos, Maarten Stol, Jakub M. Tomczak

The framework of variational autoencoders (VAEs) provides a principled method for jointly learning latent-variable models and corresponding inference models. However, the main drawback of this approach is the blurriness of the generated images. Some studies link this effect to the objective function, namely, the (negative) log-likelihood. Here, we propose to enhance VAEs by adding a random variable that is a downscaled version of the original image and still use the log-likelihood function as the learning objective. Further, by providing the downscaled image as an input to the decoder, it can be used in a manner similar to the super-resolution. We present empirically that the proposed approach performs comparably to VAEs in terms of the negative log-likelihood, but it obtains a better FID score in data synthesis.

📄 PDF Abstract BibTeX arXiv:2006.05218

Code (1)

ioangatop/srVAE 공식 구현 pytorch

Tasks

DecoderImage GenerationSuper-Resolution

Similar Papers 제목 키워드 기반

Multiresolution Equivariant Graph Variational Autoencoder

2021-06-02 · Truong Son Hy, Risi Kondor

In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each reso…

Graph GenerationImage GenerationLink Predictionmolecular representation+1

PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational Autoencoders

2025-02-07 · Tianyu Xie, Harry Richman, Jiansi Gao, Frederick A. Matsen IV 외

Learning informative representations of phylogenetic tree structures is essential for analyzing evolutionary relationships. Classical distance-based methods have been widely used to project phylogenetic trees into Euclid…

Collaborative InferenceRepresentation Learning

Autoencoders in Function Space

2024-08-02 · Justin Bunker, Mark Girolami, Hefin Lambley, Andrew M. Stuart 외

Autoencoders have found widespread application in both their original deterministic form and in their variational formulation (VAEs). In scientific applications and in image processing it is often of interest to consider…

Image Super-Resolution With Deep Variational Autoencoders

2022-03-17 · Darius Chira, Ilian Haralampiev, Ole Winther, Andrea Dittadi 외

Image super-resolution (SR) techniques are used to generate a high-resolution image from a low-resolution image. Until now, deep generative models such as autoregressive models and Generative Adversarial Networks (GANs) …

Image GenerationImage Super-ResolutionSuper-ResolutionTransfer Learning

Variational Autoencoding Neural Operators

2023-02-20 · Jacob H. Seidman, Georgios Kissas, George J. Pappas, Paris Perdikaris

Unsupervised learning with functional data is an emerging paradigm of machine learning research with applications to computer vision, climate modeling and physical systems. A natural way of modeling functional data is by…

Operator learning