paper-with-me

Papers

Spatial-Frequency U-Net for Denoising Diffusion Probabilistic Models

2023-07-27 · Xin Yuan, Linjie Li, JianFeng Wang, Zhengyuan Yang, Kevin Lin, Zicheng Liu, Lijuan Wang

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.

📄 PDF Abstract BibTeX arXiv:2307.14648

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
U-Net 설명 없음

Similar Papers 제목 키워드 기반

Rician Denoising Diffusion Probabilistic Models For Sodium Breast MRI Enhancement

2024-10-15 · Shuaiyu Yuan, Tristan Whitmarsh, Dimitri A Kessler, Otso Arponen 외

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 Assessment

DiffSVC: A Diffusion Probabilistic Model for Singing Voice Conversion

2021-05-28 · Songxiang Liu, Yuewen Cao, Dan Su, Helen Meng

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 Similarity

N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting

2026-03-07 · Yucheng Xing, Xin Wang arxiv

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 Efficiency

SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening

2024-04-17 · Yu Zhong, Xiao Wu, Liang-Jian Deng, ZiHan Cao

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 GenerationPansharpening

Elucidating the SNR-t Bias of Diffusion Probabilistic Models

2026-04-17 · Meng Yu, Lei Sun, Jianhao Zeng, Xiangxiang Chu 외 arxiv

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…