N
Norihiko Kawai
Researcher at Nara Institute of Science and Technology
Publications - 39
Citations - 412
Norihiko Kawai is an academic researcher from Nara Institute of Science and Technology. The author has contributed to research in topics: Inpainting & Pixel. The author has an hindex of 10, co-authored 35 publications receiving 347 citations. Previous affiliations of Norihiko Kawai include University of California, Berkeley & Japan Society for the Promotion of Science.
Papers
More filters
Book ChapterDOI
Image Inpainting Considering Brightness Change and Spatial Locality of Textures and Its Evaluation
TL;DR: In this paper, a new energy function based on the pattern similarity considering brightness changes of sample textures and introducing spatial locality as an additional constraint is proposed, which is successfully demonstrated by qualitative and quantitative evaluation.
Journal ArticleDOI
Diminished Reality Based on Image Inpainting Considering Background Geometry
TL;DR: This paper proposes a new diminished reality method that considers background geometries with less constraints than the conventional ones, and improves the quality of image inpainting by correcting the perspective distortion of texture and limiting the search area for finding similar textures as exemplars.
Proceedings ArticleDOI
Diminished reality considering background structures
TL;DR: This paper proposes a new diminished reality method for 3D scenes considering background structures by the combination of local planes, perspective distortion of texture is corrected and searching area is limited for improving the quality of image inpainting.
Journal ArticleDOI
[Paper] Diminished Reality for AR Marker Hiding Based on Image Inpainting with Reflection of Luminance Changes
TL;DR: In this study, assuming that an area around a marker is locally planar, the marker area in the first frame image is inpainted using the rectified image to achieve high-quality inpainting.
Proceedings Article
Image inpainting considering symmetric patterns
Norihiko Kawai,Naokazu Yokoya +1 more
TL;DR: A novel image inpainting method to remove undesired objects in an image by taking into account symmetric transformation of texture patterns to increase exemplars and defines a new degree of confidence of exemplars for determining pixel values.