Generalized Lightness Adaptation with Channel Selective Normalization
This addresses the generalization issue in image processing tasks like low-light enhancement for researchers and practitioners, though it is incremental as it builds on existing normalization techniques.
The paper tackles the problem of limited generalization in lightness adaptation methods for image processing by proposing Channel Selective Normalization (CSNorm), which improves feature generalization and discrimination, enabling models trained on one lightness condition to perform well on unknown conditions, as demonstrated on multiple benchmark datasets.
Lightness adaptation is vital to the success of image processing to avoid unexpected visual deterioration, which covers multiple aspects, e.g., low-light image enhancement, image retouching, and inverse tone mapping. Existing methods typically work well on their trained lightness conditions but perform poorly in unknown ones due to their limited generalization ability. To address this limitation, we propose a novel generalized lightness adaptation algorithm that extends conventional normalization techniques through a channel filtering design, dubbed Channel Selective Normalization (CSNorm). The proposed CSNorm purposely normalizes the statistics of lightness-relevant channels and keeps other channels unchanged, so as to improve feature generalization and discrimination. To optimize CSNorm, we propose an alternating training strategy that effectively identifies lightness-relevant channels. The model equipped with our CSNorm only needs to be trained on one lightness condition and can be well generalized to unknown lightness conditions. Experimental results on multiple benchmark datasets demonstrate the effectiveness of CSNorm in enhancing the generalization ability for the existing lightness adaptation methods. Code is available at https://github.com/mdyao/CSNorm.