SNIC: Synthesized Noisy Images using Calibration

TL;DR

This paper introduces a calibration pipeline for realistic heteroscedastic noise modeling in images, creating the SNIC dataset with over 6600 images to improve denoising model training.

Contribution

It presents a novel calibration method for heteroscedastic noise models, along with the SNIC dataset, enhancing the realism of synthetic noise for denoising research.

Findings

Synthesized noisy images reduce PSNR gap to real noise by 54-64%.

SNIC dataset includes paired RAW and TIFF data for 30 scenes and four sensors.

Open-source code enables replication and further research.

Abstract

Training advanced denoising models requires large datasets of high-fidelity, physically accurate images. While heteroscedastic noise models can simulate realistic noise, methodologies for their calibration remain under-explored, and large-scale calibrated datasets are scarce. We present a rigorous calibration and tuning pipeline for building high-quality heteroscedastic noise models across a range of sensors, incorporating dark frames to capture signal-independent noise. When evaluated with a state-of-the-art denoiser, our synthesized noisy RAW images reduce the Peak Signal to Noise Ratio (PSNR) gap to real-world noise by 54-64% compared to synthesized RAW images created using manufacturer-provided noise profiles, which fail to account for smart-phone ISP processing that suppresses noise in RAW files during calibration. Leveraging our pipeline, we introduce the Synthesized Noisy Images using Calibration (SNIC) dataset: over 6600 images across 30 scenes and four sensors (DSLR, point-and-shoot, and smartphone), with open-source calibration code and noise models. To our knowledge, SNIC is the only publicly available dataset with calibrated synthesized noise providing paired RAW and TIFF data, offering a new resource for researchers developing noise reduction models.