Learning Continuous Implicit Representation for Near-Periodic Patterns. (arXiv:2208.12278v1 [cs.CV])

Near-Periodic Patterns (NPP) are ubiquitous in man-made scenes and are
composed of tiled motifs with appearance differences caused by lighting,
defects, or design elements. A good NPP representation is useful for many
applications including image completion, segmentation, and geometric remapping.
But representing NPP is challenging because it needs to maintain global
consistency (tiled motifs layout) while preserving local variations (appearance
differences). Methods trained on general scenes using a large dataset or
single-image optimization struggle to satisfy these constraints, while methods …

arxiv continuous cv learning near patterns representation