Adaptive Domain Learning for Cross-domain Image Denoising

TL;DR

This paper proposes an adaptive domain learning scheme for cross-domain RAW image denoising that efficiently utilizes data from multiple sensors and a small amount of target sensor data to improve denoising performance.

Contribution

It introduces a novel adaptive domain learning method with a modulation module to handle sensor-specific information, enhancing cross-domain denoising with minimal target data.

Findings

Outperforms prior methods on public datasets

Effectively utilizes small target domain data

Automatically filters harmful source domain data

Abstract

Different camera sensors have different noise patterns, and thus an image denoising model trained on one sensor often does not generalize well to a different sensor. One plausible solution is to collect a large dataset for each sensor for training or fine-tuning, which is inevitably time-consuming. To address this cross-domain challenge, we present a novel adaptive domain learning (ADL) scheme for cross-domain RAW image denoising by utilizing existing data from different sensors (source domain) plus a small amount of data from the new sensor (target domain). The ADL training scheme automatically removes the data in the source domain that are harmful to fine-tuning a model for the target domain (some data are harmful as adding them during training lowers the performance due to domain gaps). Also, we introduce a modulation module to adopt sensor-specific information (sensor type and ISO) to understand input data for image denoising. We conduct extensive experiments on public datasets with various smartphone and DSLR cameras, which show our proposed model outperforms prior work on cross-domain image denoising, given a small amount of image data from the target domain sensor.