Wavelet-based Variational Autoencoders for High-Resolution Image Generation
Variational Autoencoders (VAEs) are powerful generative models capable of learning compact latent representations. However, conventional VAEs often generate relatively blurry images due to their assumption of an isotropic Gaussian latent space and constraints in capturing high-frequency details. In this paper, we explore a novel wavelet-based approach (Wavelet-VAE) in which the latent space is constructed using multi-scale Haar wavelet coefficients. We propose a comprehensive method to encode the image features into multi-scale detail and approximation coefficients and introduce a learnable noise parameter to maintain stochasticity. We thoroughly discuss how to reformulate the reparameterization trick, address the KL divergence term, and integrate wavelet sparsity principles into the training objective. Our experimental evaluation on CIFAR-10 and other high-resolution datasets demonstrates that the Wavelet-VAE improves visual fidelity and recovers higher-resolution details compared to conventional VAEs. We conclude with a discussion of advantages, potential limitations, and future research directions for wavelet-based generative modeling.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationSimilar Papers 제목 키워드 기반
LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models
Advances in latent diffusion models (LDMs) have revolutionized high-resolution image generation, but the design space of the autoencoder that is central to these systems remains underexplored. In this paper, we introduce…
Computational EfficiencyDecoderGPUImage Generation+1Wavelet Design in a Learning Framework
Wavelets have proven to be highly successful in several signal and image processing applications. Wavelet design has been an active field of research for over two decades, with the problem often being approached from an …
Discrete Wavelet Transform as a Facilitator for Expressive Latent Space Representation in Variational Autoencoders in Satellite Imagery
Latent Diffusion Models (LDM), a subclass of diffusion models, mitigate the computational complexity of pixel-space diffusion by operating within a compressed latent space constructed by Variational Autoencoders (VAEs), …
Dimension Reduction for time series with Variational AutoEncoders
In this work, we explore dimensionality reduction techniques for univariate and multivariate time series data. We especially conduct a comparison between wavelet decomposition and convolutional variational autoencoders f…
Dimensionality ReductionTime SeriesTime Series AnalysisWavelets to the Rescue: Improving Sample Quality of Latent Variable Deep Generative Models
Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations. However, they produce blurry images due to a lack…
Decoder