Realistic Noise Synthesis with Diffusion Models
This addresses a domain-specific problem for computer vision researchers and practitioners by providing a more effective way to generate training data for denoising tasks, though it is incremental as it builds on diffusion models.
The paper tackles the challenge of synthesizing realistic noise for training deep denoising models by proposing a diffusion-based method with camera-conditioned and multi-scale modules, which outperforms existing techniques in noise synthesis and improves denoising performance.
Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis Diffusor (RNSD) method using diffusion models to address these challenges. By encoding camera settings into a time-aware camera-conditioned affine modulation (TCCAM), RNSD generates more realistic noise distributions under various camera conditions. Additionally, RNSD integrates a multi-scale content-aware module (MCAM), enabling the generation of structured noise with spatial correlations across multiple frequencies. We also introduce Deep Image Prior Sampling (DIPS), a learnable sampling sequence based on depth image prior, which significantly accelerates the sampling process while maintaining the high quality of synthesized noise. Extensive experiments demonstrate that our RNSD method significantly outperforms existing techniques in synthesizing realistic noise under multiple metrics and improving image denoising performance.