Saved in:
Bibliographic Details
Main Author: Kong, Fei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.13387
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908707396255744
author Kong, Fei
author_facet Kong, Fei
contents Denoising diffusion models have emerged as a dominant paradigm in image generation. Discretizing image data into tokens is a critical step for effectively integrating images with Transformer and other architectures. Although the Denoising Diffusion Codebook Models (DDCM) pioneered the use of pre-trained diffusion models for image tokenization, it strictly relies on the traditional discrete-time DDPM architecture. Consequently, it fails to adapt to modern continuous-time variants-such as Flow Matching and Consistency Models-and suffers from inefficient sampling in high-noise regions. To address these limitations, this paper proposes the Generalized Denoising Diffusion Codebook Models (gDDCM). We establish a unified theoretical framework and introduce a generic "De-noise and Back-trace" sampling strategy. By integrating a deterministic ODE denoising step with a residual-aligned noise injection step, our method resolves the challenge of adaptation. Furthermore, we introduce a backtracking parameter $p$ and significantly enhance tokenization ability. Extensive experiments on CIFAR10 and LSUN Bedroom datasets demonstrate that gDDCM achieves comprehensive compatibility with mainstream diffusion variants and significantly outperforms DDCM in terms of reconstruction quality and perceptual fidelity.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13387
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalized Denoising Diffusion Codebook Models (gDDCM): Tokenizing images using a pre-trained diffusion model
Kong, Fei
Computer Vision and Pattern Recognition
Artificial Intelligence
Denoising diffusion models have emerged as a dominant paradigm in image generation. Discretizing image data into tokens is a critical step for effectively integrating images with Transformer and other architectures. Although the Denoising Diffusion Codebook Models (DDCM) pioneered the use of pre-trained diffusion models for image tokenization, it strictly relies on the traditional discrete-time DDPM architecture. Consequently, it fails to adapt to modern continuous-time variants-such as Flow Matching and Consistency Models-and suffers from inefficient sampling in high-noise regions. To address these limitations, this paper proposes the Generalized Denoising Diffusion Codebook Models (gDDCM). We establish a unified theoretical framework and introduce a generic "De-noise and Back-trace" sampling strategy. By integrating a deterministic ODE denoising step with a residual-aligned noise injection step, our method resolves the challenge of adaptation. Furthermore, we introduce a backtracking parameter $p$ and significantly enhance tokenization ability. Extensive experiments on CIFAR10 and LSUN Bedroom datasets demonstrate that gDDCM achieves comprehensive compatibility with mainstream diffusion variants and significantly outperforms DDCM in terms of reconstruction quality and perceptual fidelity.
title Generalized Denoising Diffusion Codebook Models (gDDCM): Tokenizing images using a pre-trained diffusion model
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.13387