Synergy Between Semantic Segmentation and Image Denoising via Alternate Boosting
This work addresses the issue of noisy input degrading segmentation performance for computer vision applications, but it is incremental as it builds on existing deep learning methods for denoising and segmentation.
The paper tackles the problem of image semantic segmentation under noisy conditions by proposing a holistic deep model that alternately performs denoising and segmentation, resulting in substantial improvements in denoised image quality and segmentation accuracy close to that of clean images.
The capability of image semantic segmentation may be deteriorated due to noisy input image, where image denoising prior to segmentation helps. Both image denoising and semantic segmentation have been developed significantly with the advance of deep learning. Thus, we are interested in the synergy between them by using a holistic deep model. We observe that not only denoising helps combat the drop of segmentation accuracy due to noise, but also pixel-wise semantic information boosts the capability of denoising. We then propose a boosting network to perform denoising and segmentation alternately. The proposed network is composed of multiple segmentation and denoising blocks (SDBs), each of which estimates semantic map then uses the map to regularize denoising. Experimental results show that the denoised image quality is improved substantially and the segmentation accuracy is improved to close to that of clean images. Our code and models will be made publicly available.