Finding Badly Drawn Bunnies

As lovely as bunnies are, your sketched version would probably not do it justice (Fig. 1). This paper recognises this very problem and studies sketch quality measurement for the first time - letting you find these badly drawn ones. Our key discovery lies in exploiting the magnitude ( L 2 norm) of a...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 7472 - 7481
Hlavní autori: Yang, Lan, Pang, Kaiyue, Zhang, Honggang, Song, Yi-Zhe
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.06.2022
Predmet:
Annotations
categorization
Computer vision
grouping and shape analysis; Vision + graphics; Vision applications and systems
Machine vision
Recognition: detection
Representation learning
retrieval; Representation learning; Segmentation
Shape
Three-dimensional displays
Time measurement
ISSN:1063-6919
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:As lovely as bunnies are, your sketched version would probably not do it justice (Fig. 1). This paper recognises this very problem and studies sketch quality measurement for the first time - letting you find these badly drawn ones. Our key discovery lies in exploiting the magnitude ( L 2 norm) of a sketch feature as a quantitative quality metric. We propose Geometry-Aware Classification Layer (GACL), a generic method that makes feature-magnitude-as-quality-metric possible and importantly does it without the need for specific quality annotations from humans. GACL sees feature magnitude and recognisability learning as a dual task, which can be simultaneously optimised under a neat crossentropy classification loss. GACL is lightweight with theoretic guarantees and enjoys a nice geometric interpretation to reason its success. We confirm consistent quality agreements between our GACL-induced metric and human perception through a carefully designed human study. Notably, we demonstrate three practical sketch applications enabled for the first time using our quantitative quality metric.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.00733