A 3D Flower Modeling Method Based on a Single Image - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

A 3D Flower Modeling Method Based on a Single Image

Ju Ming
  • Fonction : Auteur
  • PersonId : 1135975
Zhu Siyuan
  • Fonction : Auteur
  • PersonId : 1135976
Wang Meili
  • Fonction : Auteur
  • PersonId : 1135909
Lin Jiaxian
  • Fonction : Auteur
  • PersonId : 1135977

Résumé

Since the structure of the flower is too complex, the modeling of the flower faces huge challenges. This paper collects 3D scenes containing flower models, uses 3dsMax to extract flower models, and constructs flower dataset. This paper proposes an encoder-decoder network structure called MVF3D and adopted the trained MVF3D network to predict the missing perspective information, use a single RGB image to generate a depth map of flowers from different perspectives, and finally use the depth maps to reconstruct the flower models. To evaluate the performance of our proposed method, for simple flowers, the average chamfer distance between the reconstructed 3D model and the real model is 0.27, The experimental results have shown that our proposed method can preserve the true structure of the flower.
Fichier principal
Vignette du fichier
500145_1_En_38_Chapter.pdf (490.89 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03686041 , version 1 (02-06-2022)

Licence

Paternité

Identifiants

Citer

Ju Ming, Zhu Siyuan, Wang Meili, Lin Jiaxian. A 3D Flower Modeling Method Based on a Single Image. 19th International Conference on Entertainment Computing (ICEC), Nov 2020, Xi'an, China. pp.422-433, ⟨10.1007/978-3-030-65736-9_38⟩. ⟨hal-03686041⟩
16 Consultations
44 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More