Artículo
SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings
Fecha de publicación:
02/2021
Editorial:
Wiley Blackwell Publishing, Inc
Revista:
Computer Graphics Forum
ISSN:
0167-7055
Idioma:
Inglés
Tipo de recurso:
Artículo publicado
Clasificación temática:
Resumen
Finding point-wise correspondences between images is a long-standing problem in image analysis. This becomes particularly challenging for sketch images, due to the varying nature of human drawing style, projection distortions and viewport changes. In this paper, we present the first attempt to obtain a learned descriptor for dense registration in line drawings. Based on recent deep learning techniques for corresponding photographs, we designed descriptors to locally match image pairs where the object of interest belongs to the same semantic category, yet still differ drastically in shape, form, and projection angle. To this end, we have specifically crafted a data set of synthetic sketches using non-photorealistic rendering over a large collection of part-based registered 3D models. After training, a neural network generates descriptors for every pixel in an input image, which are shown togeneralize correctly in unseen sketches hand-drawn by humans. We evaluate our method against a baseline of correspondences data collected from expert designers, in addition to comparisons with other descriptors that have been proven effective in sketches. Code, data and further resources will be publicly released by the time of publication.
Archivos asociados
Licencia
Identificadores
Colecciones
Articulos(CCT - BAHIA BLANCA)
Articulos de CTRO.CIENTIFICO TECNOL.CONICET - BAHIA BLANCA
Articulos de CTRO.CIENTIFICO TECNOL.CONICET - BAHIA BLANCA
Articulos(CCT - TANDIL)
Articulos de CTRO CIENTIFICO TECNOLOGICO CONICET - TANDIL
Articulos de CTRO CIENTIFICO TECNOLOGICO CONICET - TANDIL
Articulos(IPCSH)
Articulos de INSTITUTO PATAGONICO DE CIENCIAS SOCIALES Y HUMANAS
Articulos de INSTITUTO PATAGONICO DE CIENCIAS SOCIALES Y HUMANAS
Articulos(SEDE CENTRAL)
Articulos de SEDE CENTRAL
Articulos de SEDE CENTRAL
Citación
Navarro, Jose Pablo; Orlando, José Ignacio; Delrieux, Claudio Augusto; Iarussi, Emmanuel; SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings; Wiley Blackwell Publishing, Inc; Computer Graphics Forum; 40; 1; 2-2021; 410-423
Compartir
Altmétricas