TMSDNet: Transformer with multi‐scale dense network for single and multi‐view 3D reconstruction

• Published in: Computer animation and virtual worlds Vol. 35; no. 1
• Main Authors: Zhu, Xiaoqiang, Yao, Xinsheng, Zhang, Junjie, Zhu, Mengyao, You, Lihua, Yang, Xiaosong, Zhang, Jianjun, Zhao, He, Zeng, Dan
• Format: Journal Article
• Language: English
• Published: Chichester Wiley Subscription Services, Inc 01.01.2024
• Subjects: deep learning; Feature extraction; Image reconstruction; multi‐scale; single‐view and multi‐view 3D reconstruction; transformer; Transformers

3D reconstruction is a long‐standing problem. Recently, a number of studies have emerged that utilize transformers for 3D reconstruction, and these approaches have demonstrated strong performance. However, transformer‐based 3D reconstruction methods tend to establish the transformation relationship...