Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288396918> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4288396918 abstract "Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior that captures rich image semantics including color, spatial coherence, textures, and high-level concepts. This work presents an effective way to exploit the image prior captured by a generative adversarial network (GAN) trained on large-scale natural images. As shown in Fig.1, the deep generative prior (DGP) provides compelling results to restore missing semantics, e.g., color, patch, resolution, of various degraded images. It also enables diverse image manipulation including random jittering, image morphing, and category transfer. Such highly flexible restoration and manipulation are made possible through relaxing the assumption of existing GAN-inversion methods, which tend to fix the generator. Notably, we allow the generator to be fine-tuned on-the-fly in a progressive manner regularized by feature distance obtained by the discriminator in GAN. We show that these easy-to-implement and practical changes help preserve the reconstruction to remain in the manifold of nature image, and thus lead to more precise and faithful reconstruction for real images. Code is available at https://github.com/XingangPan/deep-generative-prior." @default.
- W4288396918 created "2022-07-29" @default.
- W4288396918 creator A5005626854 @default.
- W4288396918 creator A5010087030 @default.
- W4288396918 creator A5040988693 @default.
- W4288396918 creator A5052549072 @default.
- W4288396918 creator A5075158591 @default.
- W4288396918 creator A5086484914 @default.
- W4288396918 date "2020-03-30" @default.
- W4288396918 modified "2023-09-23" @default.
- W4288396918 title "Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation" @default.
- W4288396918 doi "https://doi.org/10.48550/arxiv.2003.13659" @default.
- W4288396918 hasPublicationYear "2020" @default.
- W4288396918 type Work @default.
- W4288396918 citedByCount "0" @default.
- W4288396918 crossrefType "posted-content" @default.
- W4288396918 hasAuthorship W4288396918A5005626854 @default.
- W4288396918 hasAuthorship W4288396918A5010087030 @default.
- W4288396918 hasAuthorship W4288396918A5040988693 @default.
- W4288396918 hasAuthorship W4288396918A5052549072 @default.
- W4288396918 hasAuthorship W4288396918A5075158591 @default.
- W4288396918 hasAuthorship W4288396918A5086484914 @default.
- W4288396918 hasBestOaLocation W42883969181 @default.
- W4288396918 hasConcept C106430172 @default.
- W4288396918 hasConcept C108583219 @default.
- W4288396918 hasConcept C115961682 @default.
- W4288396918 hasConcept C121332964 @default.
- W4288396918 hasConcept C138885662 @default.
- W4288396918 hasConcept C153180895 @default.
- W4288396918 hasConcept C154945302 @default.
- W4288396918 hasConcept C163258240 @default.
- W4288396918 hasConcept C184337299 @default.
- W4288396918 hasConcept C199360897 @default.
- W4288396918 hasConcept C2776401178 @default.
- W4288396918 hasConcept C2779803651 @default.
- W4288396918 hasConcept C2780992000 @default.
- W4288396918 hasConcept C31972630 @default.
- W4288396918 hasConcept C39890363 @default.
- W4288396918 hasConcept C41008148 @default.
- W4288396918 hasConcept C41895202 @default.
- W4288396918 hasConcept C50637493 @default.
- W4288396918 hasConcept C62520636 @default.
- W4288396918 hasConcept C76155785 @default.
- W4288396918 hasConcept C9417928 @default.
- W4288396918 hasConcept C94915269 @default.
- W4288396918 hasConceptScore W4288396918C106430172 @default.
- W4288396918 hasConceptScore W4288396918C108583219 @default.
- W4288396918 hasConceptScore W4288396918C115961682 @default.
- W4288396918 hasConceptScore W4288396918C121332964 @default.
- W4288396918 hasConceptScore W4288396918C138885662 @default.
- W4288396918 hasConceptScore W4288396918C153180895 @default.
- W4288396918 hasConceptScore W4288396918C154945302 @default.
- W4288396918 hasConceptScore W4288396918C163258240 @default.
- W4288396918 hasConceptScore W4288396918C184337299 @default.
- W4288396918 hasConceptScore W4288396918C199360897 @default.
- W4288396918 hasConceptScore W4288396918C2776401178 @default.
- W4288396918 hasConceptScore W4288396918C2779803651 @default.
- W4288396918 hasConceptScore W4288396918C2780992000 @default.
- W4288396918 hasConceptScore W4288396918C31972630 @default.
- W4288396918 hasConceptScore W4288396918C39890363 @default.
- W4288396918 hasConceptScore W4288396918C41008148 @default.
- W4288396918 hasConceptScore W4288396918C41895202 @default.
- W4288396918 hasConceptScore W4288396918C50637493 @default.
- W4288396918 hasConceptScore W4288396918C62520636 @default.
- W4288396918 hasConceptScore W4288396918C76155785 @default.
- W4288396918 hasConceptScore W4288396918C9417928 @default.
- W4288396918 hasConceptScore W4288396918C94915269 @default.
- W4288396918 hasLocation W42883969181 @default.
- W4288396918 hasOpenAccess W4288396918 @default.
- W4288396918 hasPrimaryLocation W42883969181 @default.
- W4288396918 hasRelatedWork W11273282 @default.
- W4288396918 hasRelatedWork W11424074 @default.
- W4288396918 hasRelatedWork W12455713 @default.
- W4288396918 hasRelatedWork W13187899 @default.
- W4288396918 hasRelatedWork W2988963 @default.
- W4288396918 hasRelatedWork W3238102 @default.
- W4288396918 hasRelatedWork W4827971 @default.
- W4288396918 hasRelatedWork W8340350 @default.
- W4288396918 hasRelatedWork W9871412 @default.
- W4288396918 hasRelatedWork W1660204 @default.
- W4288396918 isParatext "false" @default.
- W4288396918 isRetracted "false" @default.
- W4288396918 workType "article" @default.