A Topological Loss Function: Image Denoising on a Low-Light Dataset
Although image denoising algorithms have attracted significant research attention, surprisingly few have been proposed for, or evaluated on, noise from imagery acquired under real low-light conditions. Moreover, noise characteristics are often assumed to be spatially invariant, leading to edges and textures being distorted after denoising. Here, we introduce a novel topological loss function which is based on persistent homology. The method performs in the space of image patches, where topological invariants are calculated and represented in persistent diagrams. The loss function is a combination of $\ell_1$ or $\ell_2$ losses with the new persistence-based topological loss. We compare its performance across popular denoising architectures and loss functions, training the networks on our new comprehensive dataset of natural images captured in low-light conditions -- BVI-LOWLIGHT. Analysis reveals that this approach outperforms existing methods, adapting well to complex structures and suppressing common artifacts.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingImage DenoisingSimilar Papers 제목 키워드 기반
Wavelet-based Topological Loss for Low-Light Image Denoising
Despite extensive research conducted in the field of image denoising, many algorithms still heavily depend on supervised learning and their effectiveness primarily relies on the quality and diversity of training data. It…
DenoisingImage DenoisingStructure-Aware Image Segmentation with Homotopy Warping
Besides per-pixel accuracy, topological correctness is also crucial for the segmentation of images with fine-scale structures, e.g., satellite images and biomedical images. In this paper, by leveraging the theory of digi…
Image SegmentationSegmentationSemantic SegmentationEuler Characteristic Transform Based Topological Loss for Reconstructing 3D Images from Single 2D Slices
The computer vision task of reconstructing 3D images, i.e., shapes, from their single 2D image slices is extremely challenging, more so in the regime of limited data. Deep learning models typically optimize geometric los…
Inductive BiasLuminanceL1Loss: A loss function which measures percieved brightness and colour differences
We introduce LuminanceL1Loss, a novel loss function designed to enhance the performance of image restoration tasks. We demonstrate its superiority over MSE when applied to the Retinexformer, BUIFD and DnCNN architectures…
DenoisingImage DenoisingImage ReconstructionImage RestorationVisualizing Loss Functions as Topological Landscape Profiles
In machine learning, a loss function measures the difference between model predictions and ground-truth (or target) values. For neural network models, visualizing how this loss changes as model parameters are varied can …
Image SegmentationSemantic SegmentationTopological Data Analysis