2021 IEEE International Conference on Image Processing
19-22 September 2021 • Anchorage, Alaska, USA
Imaging Without Borders
| Paper ID | TEC-1.4 | ||
| Paper Title | DEEP GAUSSIAN DENOISER EPISTEMIC UNCERTAINTY AND DECOUPLED DUAL-ATTENTION FUSION | ||
| Authors | Xiaoqi Ma, Xiaoyu Lin, Majed El Helou, Sabine Süsstrunk, École Polytechnique Fédérale de Lausanne (EPFL), Switzerland | ||
| Session | TEC-1: Restoration and Enhancement 1 | ||
| Location | Area G | ||
| Session Time: | Tuesday, 21 September, 13:30 - 15:00 | ||
| Presentation Time: | Tuesday, 21 September, 13:30 - 15:00 | ||
| Presentation | Poster | ||
| Topic | Image and Video Processing: Restoration and enhancement | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | Following the performance breakthrough of denoising networks, improvements have come chiefly through novel architecture designs and increased depth. While novel denoising networks were designed for real images coming from different distributions, or for specific applications, comparatively small improvement was achieved on Gaussian denoising. The denoising solutions suffer from epistemic uncertainty that can limit further advancements. This uncertainty is traditionally mitigated through different ensemble approaches. However, such ensembles are prohibitively costly with deep networks, which are already large in size. Our work focuses on pushing the performance limits of state-of-the-art methods on Gaussian denoising. We propose a model-agnostic approach for reducing epistemic uncertainty while using only a single pretrained network. We achieve this by tapping into the epistemic uncertainty through augmented and frequency-manipulated images to obtain denoised images with varying error. We propose an ensemble method with two decoupled attention paths, over the pixel domain and over that of our different manipulations, to learn the final fusion. Our results significantly improve over the state-of-the-art baselines and across varying noise levels. | ||