Copy-and-Paste Networks fill video holes using a self-supervised alignment network and masked softmax context matching, reaching quality similar to optimization-based methods at a fraction of the runtime.
Patchmatch: a randomized correspondence algorithm for structural image editing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Copy-and-Paste Networks for Deep Video Inpainting
Copy-and-Paste Networks fill video holes using a self-supervised alignment network and masked softmax context matching, reaching quality similar to optimization-based methods at a fraction of the runtime.