Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386875199> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4386875199 abstract "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 is widely assumed that digital image distortions are caused by spatially invariant Additive White Gaussian Noise (AWGN). However, the analysis of real-world data suggests that this assumption is invalid. Therefore, this paper tackles image corruption by real noise, providing a framework to capture and utilise the underlying structural information of an image along with the spatial information conventionally used for deep learning tasks. We propose a novel denoising loss function that incorporates topological invariants and is informed by textural information extracted from the image wavelet domain. The effectiveness of this proposed method was evaluated by training state-of-the-art denoising models on the BVI-Lowlight dataset, which features a wide range of real noise distortions. Adding a topological term to common loss functions leads to a significant increase in the LPIPS (Learned Perceptual Image Patch Similarity) metric, with the improvement reaching up to 25%. The results indicate that the proposed loss function enables neural networks to learn noise characteristics better. We demonstrate that they can consequently extract the topological features of noise-free images, resulting in enhanced contrast and preserved textural information." @default.
- W4386875199 created "2023-09-20" @default.
- W4386875199 creator A5015307291 @default.
- W4386875199 creator A5021717616 @default.
- W4386875199 creator A5048009053 @default.
- W4386875199 date "2023-09-16" @default.
- W4386875199 modified "2023-10-18" @default.
- W4386875199 title "Wavelet-based Topological Loss for Low-Light Image Denoising" @default.
- W4386875199 doi "https://doi.org/10.48550/arxiv.2309.08975" @default.
- W4386875199 hasPublicationYear "2023" @default.
- W4386875199 type Work @default.
- W4386875199 citedByCount "0" @default.
- W4386875199 crossrefType "posted-content" @default.
- W4386875199 hasAuthorship W4386875199A5015307291 @default.
- W4386875199 hasAuthorship W4386875199A5021717616 @default.
- W4386875199 hasAuthorship W4386875199A5048009053 @default.
- W4386875199 hasBestOaLocation W43868751991 @default.
- W4386875199 hasConcept C101453961 @default.
- W4386875199 hasConcept C112633086 @default.
- W4386875199 hasConcept C115961682 @default.
- W4386875199 hasConcept C153180895 @default.
- W4386875199 hasConcept C154945302 @default.
- W4386875199 hasConcept C163294075 @default.
- W4386875199 hasConcept C169334058 @default.
- W4386875199 hasConcept C2983327147 @default.
- W4386875199 hasConcept C41008148 @default.
- W4386875199 hasConcept C4199805 @default.
- W4386875199 hasConcept C47432892 @default.
- W4386875199 hasConcept C55020928 @default.
- W4386875199 hasConcept C76155785 @default.
- W4386875199 hasConcept C99498987 @default.
- W4386875199 hasConceptScore W4386875199C101453961 @default.
- W4386875199 hasConceptScore W4386875199C112633086 @default.
- W4386875199 hasConceptScore W4386875199C115961682 @default.
- W4386875199 hasConceptScore W4386875199C153180895 @default.
- W4386875199 hasConceptScore W4386875199C154945302 @default.
- W4386875199 hasConceptScore W4386875199C163294075 @default.
- W4386875199 hasConceptScore W4386875199C169334058 @default.
- W4386875199 hasConceptScore W4386875199C2983327147 @default.
- W4386875199 hasConceptScore W4386875199C41008148 @default.
- W4386875199 hasConceptScore W4386875199C4199805 @default.
- W4386875199 hasConceptScore W4386875199C47432892 @default.
- W4386875199 hasConceptScore W4386875199C55020928 @default.
- W4386875199 hasConceptScore W4386875199C76155785 @default.
- W4386875199 hasConceptScore W4386875199C99498987 @default.
- W4386875199 hasLocation W43868751991 @default.
- W4386875199 hasOpenAccess W4386875199 @default.
- W4386875199 hasPrimaryLocation W43868751991 @default.
- W4386875199 hasRelatedWork W1487093003 @default.
- W4386875199 hasRelatedWork W2016150650 @default.
- W4386875199 hasRelatedWork W2062171491 @default.
- W4386875199 hasRelatedWork W2141338552 @default.
- W4386875199 hasRelatedWork W2149705930 @default.
- W4386875199 hasRelatedWork W2363723763 @default.
- W4386875199 hasRelatedWork W2368505324 @default.
- W4386875199 hasRelatedWork W2368887148 @default.
- W4386875199 hasRelatedWork W2968742862 @default.
- W4386875199 hasRelatedWork W2183154457 @default.
- W4386875199 isParatext "false" @default.
- W4386875199 isRetracted "false" @default.
- W4386875199 workType "article" @default.