Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048691207> ?p ?o ?g. }
- W3048691207 abstract "Facial image inpainting is a problem that is widely studied, and in recent years the introduction of Generative Adversarial Networks, has led to improvements in the field. Unfortunately some issues persists, in particular when blending the missing pixels with the visible ones. We address the problem by proposing a Wasserstein GAN combined with a new reverse mask operator, namely Reverse Masking Network (R-MNet), a perceptual adversarial network for image inpainting. The reverse mask operator transfers the reverse masked image to the end of the encoder-decoder network leaving only valid pixels to be inpainted. Additionally, we propose a new loss function computed in feature space to target only valid pixels combined with adversarial training. These then capture data distributions and generate images similar to those in the training data with achieved realism (realistic and coherent) on the output images. We evaluate our method on publicly available dataset, and compare with state-of-the-art methods. We show that our method is able to generalize to high-resolution inpainting task, and further show more realistic outputs that are plausible to the human visual system when compared with the state-of-the-art methods." @default.
- W3048691207 created "2020-08-18" @default.
- W3048691207 creator A5015206948 @default.
- W3048691207 creator A5024763147 @default.
- W3048691207 creator A5037771946 @default.
- W3048691207 creator A5040767315 @default.
- W3048691207 creator A5085518702 @default.
- W3048691207 creator A5089692099 @default.
- W3048691207 date "2020-08-11" @default.
- W3048691207 modified "2023-09-27" @default.
- W3048691207 title "R-MNet: A Perceptual Adversarial Network for Image Inpainting" @default.
- W3048691207 cites W1834627138 @default.
- W3048691207 cites W1901129140 @default.
- W3048691207 cites W1993120651 @default.
- W3048691207 cites W2055132753 @default.
- W3048691207 cites W2099471712 @default.
- W3048691207 cites W2105038642 @default.
- W3048691207 cites W2116013899 @default.
- W3048691207 cites W2129981175 @default.
- W3048691207 cites W2133665775 @default.
- W3048691207 cites W2194775991 @default.
- W3048691207 cites W2295936755 @default.
- W3048691207 cites W2331128040 @default.
- W3048691207 cites W2476548250 @default.
- W3048691207 cites W2557414982 @default.
- W3048691207 cites W2611104282 @default.
- W3048691207 cites W2732026016 @default.
- W3048691207 cites W2738588019 @default.
- W3048691207 cites W2798365772 @default.
- W3048691207 cites W2869294161 @default.
- W3048691207 cites W2902017744 @default.
- W3048691207 cites W2947189014 @default.
- W3048691207 cites W2962760235 @default.
- W3048691207 cites W2962835968 @default.
- W3048691207 cites W2963231084 @default.
- W3048691207 cites W2963270367 @default.
- W3048691207 cites W2963420272 @default.
- W3048691207 cites W2963917315 @default.
- W3048691207 cites W2963920537 @default.
- W3048691207 cites W2963981733 @default.
- W3048691207 cites W2965965567 @default.
- W3048691207 cites W2981682056 @default.
- W3048691207 cites W2982763192 @default.
- W3048691207 cites W2985764327 @default.
- W3048691207 cites W2989207674 @default.
- W3048691207 cites W2990886896 @default.
- W3048691207 cites W2999745734 @default.
- W3048691207 cites W3026446890 @default.
- W3048691207 cites W3043547428 @default.
- W3048691207 hasPublicationYear "2020" @default.
- W3048691207 type Work @default.
- W3048691207 sameAs 3048691207 @default.
- W3048691207 citedByCount "0" @default.
- W3048691207 crossrefType "posted-content" @default.
- W3048691207 hasAuthorship W3048691207A5015206948 @default.
- W3048691207 hasAuthorship W3048691207A5024763147 @default.
- W3048691207 hasAuthorship W3048691207A5037771946 @default.
- W3048691207 hasAuthorship W3048691207A5040767315 @default.
- W3048691207 hasAuthorship W3048691207A5085518702 @default.
- W3048691207 hasAuthorship W3048691207A5089692099 @default.
- W3048691207 hasConcept C115961682 @default.
- W3048691207 hasConcept C11727466 @default.
- W3048691207 hasConcept C138885662 @default.
- W3048691207 hasConcept C153180895 @default.
- W3048691207 hasConcept C154945302 @default.
- W3048691207 hasConcept C160633673 @default.
- W3048691207 hasConcept C2776401178 @default.
- W3048691207 hasConcept C31972630 @default.
- W3048691207 hasConcept C37736160 @default.
- W3048691207 hasConcept C41008148 @default.
- W3048691207 hasConcept C41895202 @default.
- W3048691207 hasConceptScore W3048691207C115961682 @default.
- W3048691207 hasConceptScore W3048691207C11727466 @default.
- W3048691207 hasConceptScore W3048691207C138885662 @default.
- W3048691207 hasConceptScore W3048691207C153180895 @default.
- W3048691207 hasConceptScore W3048691207C154945302 @default.
- W3048691207 hasConceptScore W3048691207C160633673 @default.
- W3048691207 hasConceptScore W3048691207C2776401178 @default.
- W3048691207 hasConceptScore W3048691207C31972630 @default.
- W3048691207 hasConceptScore W3048691207C37736160 @default.
- W3048691207 hasConceptScore W3048691207C41008148 @default.
- W3048691207 hasConceptScore W3048691207C41895202 @default.
- W3048691207 hasLocation W30486912071 @default.
- W3048691207 hasOpenAccess W3048691207 @default.
- W3048691207 hasPrimaryLocation W30486912071 @default.
- W3048691207 hasRelatedWork W2479644247 @default.
- W3048691207 hasRelatedWork W2770743355 @default.
- W3048691207 hasRelatedWork W2770961787 @default.
- W3048691207 hasRelatedWork W2796286534 @default.
- W3048691207 hasRelatedWork W2901936680 @default.
- W3048691207 hasRelatedWork W2973485811 @default.
- W3048691207 hasRelatedWork W2977027504 @default.
- W3048691207 hasRelatedWork W2985764327 @default.
- W3048691207 hasRelatedWork W2993008438 @default.
- W3048691207 hasRelatedWork W3035018924 @default.
- W3048691207 hasRelatedWork W3082497595 @default.
- W3048691207 hasRelatedWork W3119307179 @default.
- W3048691207 hasRelatedWork W3120851889 @default.
- W3048691207 hasRelatedWork W3123896564 @default.
- W3048691207 hasRelatedWork W3146490099 @default.