FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel Diffusion
cs.CV
Submitted: 2026-05-18
Updated: 2026-10-13
Terminology
Sources
- PixelFlow: Pixel-Space Generative Models with Flow
- DiP: Taming Diffusion Models in Pixel Space
- Classifier-Free Diffusion Guidance
- Scalable Adaptive Computation for Iterative Generation
- Back to Basics: Let Denoising Generative Models Denoise
- Fractal Generative Models
- SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers
- DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
- PixelGen: Improving Pixel Diffusion with Perceptual Supervision
- DINOv2: Learning Robust Visual Features without Supervision
- Latent Diffusion Model without Variational Autoencoder
- Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
- JetFormer: An Autoregressive Generative Model of Raw Images and Text
- PixNerd: Pixel Neural Field Diffusion
- DDT: Decoupled Diffusion Transformer
- PixelDiT: Pixel Diffusion Transformers for Image Generation
- Diffusion Transformers with Representation Autoencoders
- FARMER: Flow AutoRegressive Transformer over Pixels
- Fast Training of Diffusion Models with Masked Transformers
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models