Training method of sketch generation model, sketch generation method, terminal and medium

The invention discloses a sketch generation model training method, a sketch generation method, a terminal and a medium, and the method comprises the steps: constructing a training data set, adding noise in the training data set, and obtaining a noise-added training data set, the training data set co...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: YAO BAOGANG, SUN WENYU, LIU XIANGDONG, JIANG PING, ZHANG NAN
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a sketch generation model training method, a sketch generation method, a terminal and a medium, and the method comprises the steps: constructing a training data set, adding noise in the training data set, and obtaining a noise-added training data set, the training data set comprising discretized graph structure data or SDF data; the training data set after noise adding is input into a deep neural network model, prediction sketch structure data are obtained, and the deep neural network model is a network model with a Transform architecture as a core or a network model with a Unet architecture as a core; and determining a loss function based on the training data set and the predicted sketch structure data, and performing iterative training on the deep neural network model based on the loss function to obtain a sketch generation model. According to the method, the data structure characteristics are exerted, the sketch generation model obtained through training can effectively solve the pr