Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sigillo, Luigi, He, Shengfeng, Comminiello, Danilo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908967020527616
author Sigillo, Luigi
He, Shengfeng
Comminiello, Danilo
author_facet Sigillo, Luigi
He, Shengfeng
Comminiello, Danilo
contents High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preservation of fine-grained visual detail. We present Latent Wavelet Diffusion (LWD), a lightweight training framework that significantly improves detail and texture fidelity in ultra-high-resolution (2K-4K) image synthesis. LWD introduces a novel, frequency-aware masking strategy derived from wavelet energy maps, which dynamically focuses the training process on detail-rich regions of the latent space. This is complemented by a scale-consistent VAE objective to ensure high spectral fidelity. The primary advantage of our approach is its efficiency: LWD requires no architectural modifications and adds zero additional cost during inference, making it a practical solution for scaling existing models. Across multiple strong baselines, LWD consistently improves perceptual quality and FID scores, demonstrating the power of signal-driven supervision as a principled and efficient path toward high-resolution generative modeling. The code is available at https://github.com/LuigiSigillo/LatentWaveletDiffusion
format Preprint
id arxiv_https___arxiv_org_abs_2506_00433
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis
Sigillo, Luigi
He, Shengfeng
Comminiello, Danilo
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preservation of fine-grained visual detail. We present Latent Wavelet Diffusion (LWD), a lightweight training framework that significantly improves detail and texture fidelity in ultra-high-resolution (2K-4K) image synthesis. LWD introduces a novel, frequency-aware masking strategy derived from wavelet energy maps, which dynamically focuses the training process on detail-rich regions of the latent space. This is complemented by a scale-consistent VAE objective to ensure high spectral fidelity. The primary advantage of our approach is its efficiency: LWD requires no architectural modifications and adds zero additional cost during inference, making it a practical solution for scaling existing models. Across multiple strong baselines, LWD consistently improves perceptual quality and FID scores, demonstrating the power of signal-driven supervision as a principled and efficient path toward high-resolution generative modeling. The code is available at https://github.com/LuigiSigillo/LatentWaveletDiffusion
title Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis
topic Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2506.00433