Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis

arXiv:2506.00433v4 Announce Type: replace Abstract: 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

Related

• PixelDiT: Pixel Diffusion Transformers for Image Generation
• RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification
• FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution
• UHD Low-Light Image Enhancement via Real-Time Enhancement Methods with Clifford Information Fusion

Source: arXiv cs.CV | 2026-04-17