paper-with-me

Papers

DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space

2024-12-19 · Mang Ning, Mingxiao Li, Jianlin Su, Haozhe Jia, Lanmiao Liu, Martin Beneš, Wenshuo Chen, Albert Ali Salah, Itir Onal Ertugrul

This paper explores image modeling from the frequency space and introduces DCTdiff, an end-to-end diffusion generative paradigm that efficiently models images in the discrete cosine transform (DCT) space. We investigate the design space of DCTdiff and reveal the key design factors. Experiments on different frameworks (UViT, DiT), generation tasks, and various diffusion samplers demonstrate that DCTdiff outperforms pixel-based diffusion models regarding generative quality and training efficiency. Remarkably, DCTdiff can seamlessly scale up to 512$\times$512 resolution without using the latent diffusion paradigm and beats latent diffusion (using SD-VAE) with only 1/4 training cost. Finally, we illustrate several intriguing properties of DCT image modeling. For example, we provide a theoretical proof of why 'image diffusion can be seen as spectral autoregression', bridging the gap between diffusion and autoregressive models. The effectiveness of DCTdiff and the introduced properties suggest a promising direction for image modeling in the frequency space. The code is https://github.com/forever208/DCTdiff.

📄 PDF Abstract BibTeX arXiv:2412.15032

Code (1)

forever208/dctdiff 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

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…
Discrete Cosine Transform Discrete Cosine Transform (DCT) is an orthogonal transformation method that decomposes an image to its spatial frequency spectrum. It expresses a finite sequence of data…

Similar Papers 제목 키워드 기반

Intriguing properties of generative classifiers

2023-09-28 · Priyank Jaini, Kevin Clark, Robert Geirhos

What is the best paradigm to recognize objects -- discriminative inference (fast but potentially prone to shortcut learning) or using a generative model (slow but potentially more robust)? We build on recent advances in …

Object Recognition

Intriguing properties of synthetic images: from generative adversarial networks to diffusion models

2023-04-13 · Riccardo Corvi, Davide Cozzolino, Giovanni Poggi, Koki Nagano 외

Detecting fake images is becoming a major goal of computer vision. This need is becoming more and more pressing with the continuous improvement of synthesis methods based on Generative Adversarial Networks (GAN), and eve…

Geometric Regularity in Deterministic Sampling of Diffusion-based Generative Models

2025-06-11 · Defang Chen, Zhenyu Zhou, Can Wang, Siwei Lyu

Diffusion-based generative models employ stochastic differential equations (SDEs) and their equivalent probability flow ordinary differential equations (ODEs) to establish a smooth transformation between complex high-dim…

Image Generation

Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective

2024-10-16 · Yongxin Zhu, Bocheng Li, Hang Zhang, Xin Li 외

Latent-based image generative models, such as Latent Diffusion Models (LDMs) and Mask Image Models (MIMs), have achieved notable success in image generation tasks. These models typically leverage reconstructive autoencod…

Conditional Image GenerationImage GenerationLinear-Probe ClassificationSelf-Supervised Image Classification+2

Semantic Preserving Generative Adversarial Models

2019-10-07 · Shahar Harel, Meir Maor, Amir Ronen

We introduce generative adversarial models in which the discriminator is replaced by a calibrated (non-differentiable) classifier repeatedly enhanced by domain relevant features. The role of the classifier is to prove th…

Transfer Learning