D$^2$-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models
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.
Code (1)
Tasks
DenoisingImage GenerationNoise EstimationQuantizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ResEnsemble-DDPM: Residual Denoising Diffusion Probabilistic Models for Ensemble Learning
Nowadays, denoising diffusion probabilistic models have been adapted for many image segmentation tasks. However, existing end-to-end models have already demonstrated remarkable capabilities. Rather than using denoising d…
DenoisingEnsemble LearningImage GenerationImage Segmentation+2Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates
Efficient compression of low-bit-rate point clouds is critical for bandwidth-constrained applications. However, existing techniques mainly focus on high-fidelity reconstruction, requiring many bits for compression. This …
DenoisingPTQD: Accurate Post-Training Quantization for Diffusion Models
Diffusion models have recently dominated image synthesis tasks. However, the iterative denoising process is expensive in computations at inference time, making diffusion models less practical for low-latency and scalable…
DenoisingImage GenerationQuantizationKidney Cancer Detection Using 3D-Based Latent Diffusion Models
In this work, we present a novel latent diffusion-based pipeline for 3D kidney anomaly detection on contrast-enhanced abdominal CT. The method combines Denoising Diffusion Probabilistic Models (DDPMs), Denoising Diffusio…
Supervised Anomaly DetectionComposer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion Models
Emerging Denoising Diffusion Probabilistic Models (DDPM) have become increasingly utilised because of promising results they have achieved in diverse generative tasks with continuous data, such as image and sound synthes…
DecoderDenoisingMusic Generation