Timezone: »

Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training
Yuanhao Cai · Xiaowan Hu · Haoqian Wang · Yulun Zhang · Hanspeter Pfister · Donglai Wei

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @ Virtual

Existing deep learning real denoising methods require a large amount of noisy-clean image pairs for supervision. Nonetheless, capturing a real noisy-clean dataset is an unacceptable expensive and cumbersome procedure. To alleviate this problem, this work investigates how to generate realistic noisy images. Firstly, we formulate a simple yet reasonable noise model that treats each real noisy pixel as a random variable. This model splits the noisy image generation problem into two sub-problems: image domain alignment and noise domain alignment. Subsequently, we propose a novel framework, namely Pixel-level Noise-aware Generative Adversarial Network (PNGAN). PNGAN employs a pre-trained real denoiser to map the fake and real noisy images into a nearly noise-free solution space to perform image domain alignment. Simultaneously, PNGAN establishes a pixel-level adversarial training to conduct noise domain alignment. Additionally, for better noise fitting, we present an efficient architecture Simple Multi-scale Network (SMNet) as the generator. Qualitative validation shows that noise generated by PNGAN is highly similar to real noise in terms of intensity and distribution. Quantitative experiments demonstrate that a series of denoisers trained with the generated noisy images achieve state-of-the-art (SOTA) results on four real denoising benchmarks.

Author Information

Yuanhao Cai (Tsinghua Shenzhen International Graduate School)
Xiaowan Hu (Tsinghua University, Tsinghua University)
Haoqian Wang (Tsinghua Shenzhen International Graduate School)
Yulun Zhang (ETH Zürich)
Hanspeter Pfister (Harvard)
Donglai Wei (Boston College)

More from the Same Authors