Spatial-Frequency U-Net for Denoising Diffusion Probabilistic Models
In this paper, we study the denoising diffusion probabilistic model (DDPM) in wavelet space, instead of pixel space, for visual synthesis. Considering the wavelet transform represents the image in spatial and frequency domains, we carefully design a novel architecture SFUNet to effectively capture the correlation for both domains. Specifically, in the standard denoising U-Net for pixel data, we supplement the 2D convolutions and spatial-only attention layers with our spatial frequency-aware convolution and attention modules to jointly model the complementary information from spatial and frequency domains in wavelet data. Our new architecture can be used as a drop-in replacement to the pixel-based network and is compatible with the vanilla DDPM training process. By explicitly modeling the wavelet signals, we find our model is able to generate images with higher quality on CIFAR-10, FFHQ, LSUN-Bedroom, and LSUN-Church datasets, than the pixel-based counterpart.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Rician Denoising Diffusion Probabilistic Models For Sodium Breast MRI Enhancement
Sodium MRI is an imaging technique used to visualize and quantify sodium concentrations in vivo, playing a role in many biological processes and potentially aiding in breast cancer characterization. Sodium MRI, however, …
DenoisingImage Quality AssessmentDiffSVC: A Diffusion Probabilistic Model for Singing Voice Conversion
Singing voice conversion (SVC) is one promising technique which can enrich the way of human-computer interaction by endowing a computer the ability to produce high-fidelity and expressive singing voice. In this paper, we…
DenoisingVoice ConversionVoice SimilarityN-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting
Long-horizon wildfire risk forecasting requires generating probabilistic spatial fields under sparse event supervision while maintaining computational efficiency across multiple prediction horizons. Extending diffusion m…
Computational EfficiencySSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening
Pansharpening is a significant image fusion technique that merges the spatial content and spectral characteristics of remote sensing images to generate high-resolution multispectral images. Recently, denoising diffusion …
DenoisingImage GenerationPansharpeningElucidating the SNR-t Bias of Diffusion Probabilistic Models
Diffusion Probabilistic Models have demonstrated remarkable performance across a wide range of generative tasks. However, we have observed that these models often suffer from a Signal-to-Noise Ratio-timestep (SNR-t) bias…