Please use this identifier to cite or link to this item:
Title: Mesh R-CNN++ for 3D Mesh generation: from single to multiple views
Authors: Zhang, HengKai
Keywords: Engineering::Computer science and engineering
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Zhang, H. (2022). Mesh R-CNN++ for 3D Mesh generation: from single to multiple views. Final Year Project (FYP), Nanyang Technological University, Singapore.
Project: SCSE21-4080
Abstract: Inferring the 3-dimensional structure and geometry of scenes and objects from one or multiple 2-dimensional images has been one of the primary goals of image-based 3D reconstruction. In recent years, with the improved progress of deep learning techniques, and the increasing availability of large 3D training datasets, led to significant advances in 3D shape understanding using deep learning. Inspired by traditional multiple view geometry methods, this project proposed, Mesh R-CNN++, a multi-view deep learning shape predictor. Extensive experiments against current state-of-the-art single and multi-view deep learning shape predictors showed that Mesh R-CNN++ produces 3D models with accurate thin structures and surface details using multiple images.
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
2.16 MBAdobe PDFView/Open

Page view(s)

Updated on May 25, 2022


Updated on May 25, 2022

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.