D$^2$-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915181131464704 |
|---|---|
| author | Zeng, Qian Song, Jie Zheng, Han Jiang, Hao Song, Mingli |
| author_facet | Zeng, Qian Song, Jie Zheng, Han Jiang, Hao Song, Mingli |
| contents | Diffusion models have achieved cutting-edge performance in image generation. However, their lengthy denoising process and computationally intensive score estimation network impede their scalability in low-latency and resource-constrained scenarios. Post-training quantization (PTQ) compresses and accelerates diffusion models without retraining, but it inevitably introduces additional quantization noise, resulting in mean and variance deviations. In this work, we propose D2-DPM, a dual denoising mechanism aimed at precisely mitigating the adverse effects of quantization noise on the noise estimation network. Specifically, we first unravel the impact of quantization noise on the sampling equation into two components: the mean deviation and the variance deviation. The mean deviation alters the drift coefficient of the sampling equation, influencing the trajectory trend, while the variance deviation magnifies the diffusion coefficient, impacting the convergence of the sampling trajectory. The proposed D2-DPM is thus devised to denoise the quantization noise at each time step, and then denoise the noisy sample through the inverse diffusion iterations. Experimental results demonstrate that D2-DPM achieves superior generation quality, yielding a 1.42 lower FID than the full-precision model while achieving 3.99x compression and 11.67x bit-operation acceleration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_08180 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | D$^2$-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models Zeng, Qian Song, Jie Zheng, Han Jiang, Hao Song, Mingli Computer Vision and Pattern Recognition Machine Learning Diffusion models have achieved cutting-edge performance in image generation. However, their lengthy denoising process and computationally intensive score estimation network impede their scalability in low-latency and resource-constrained scenarios. Post-training quantization (PTQ) compresses and accelerates diffusion models without retraining, but it inevitably introduces additional quantization noise, resulting in mean and variance deviations. In this work, we propose D2-DPM, a dual denoising mechanism aimed at precisely mitigating the adverse effects of quantization noise on the noise estimation network. Specifically, we first unravel the impact of quantization noise on the sampling equation into two components: the mean deviation and the variance deviation. The mean deviation alters the drift coefficient of the sampling equation, influencing the trajectory trend, while the variance deviation magnifies the diffusion coefficient, impacting the convergence of the sampling trajectory. The proposed D2-DPM is thus devised to denoise the quantization noise at each time step, and then denoise the noisy sample through the inverse diffusion iterations. Experimental results demonstrate that D2-DPM achieves superior generation quality, yielding a 1.42 lower FID than the full-precision model while achieving 3.99x compression and 11.67x bit-operation acceleration. |
| title | D$^2$-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2501.08180 |