Personalized Generative Low-light Image Denoising and Enhancement
This addresses low-light image quality issues for smartphone users by personalizing denoising, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of hallucinatory content generation in generative low-light image denoising by proposing a personalized diffusion model that uses an identity-consistent physical buffer from user photo galleries, achieving superior performance compared to existing diffusion-based methods.
While smartphone cameras today can produce astonishingly good photos, their performance in low light is still not completely satisfactory because of the fundamental limits in photon shot noise and sensor read noise. Generative image restoration methods have demonstrated promising results compared to traditional methods, but they suffer from hallucinatory content generation when the signal-to-noise ratio (SNR) is low. Recognizing the availability of personalized photo galleries on users' smartphones, we propose Personalized Generative Denoising (PGD) by building a diffusion model customized for different users. Our core innovation is an identity-consistent physical buffer that extracts the physical attributes of the person from the gallery. This ID-consistent physical buffer provides a strong prior that can be integrated with the diffusion model to restore the degraded images, without the need of fine-tuning. Over a wide range of low-light testing scenarios, we show that PGD achieves superior image denoising and enhancement performance compared to existing diffusion-based denoising approaches.