Reconstructing Detailed 3D Car Geometries from a Single 2D Image by Repurposing PIFu - Dalam bentuk buku karya ilmiah

FADRIANTO SULISTIYORAHMAN

Informasi Dasar

59 kali
24.04.5793
006.37
Karya Ilmiah - Skripsi (S1) - Reference

User generated content is an integral part of the Internet. With VR and AR technologies becoming more accessible and affordable, there will be increase in demand to create 3D content independently. Through AI, the process of creating 3D content for the average user can be made easier. In this study, we will focus on PIFu, one of the most prominent 2D to 3D reconstruction method. PIFu is and end-to-end deep learning method for 3D geometry reconstruction. It can also infer the texture of the object. PIFu originally focused on generating 3D geometries for humans wearing clothes with has intricate texture. In this study, we trained this model on car object categories to reconstruct detailed 3D car geometries. We evaluated the test results for 24 geometries, resulting in 0.046 ± 0.019 m, 0.344 ± 0.118 m, 0.677 ± 0.124 for average symmetric surface distance, hausdorff distance, and intersection over union, respectively. The geometries also have pronounced details most notably the clear separation between the wheels and the body.

Subjek

Image processing - computer vision
 

Katalog

Reconstructing Detailed 3D Car Geometries from a Single 2D Image by Repurposing PIFu - Dalam bentuk buku karya ilmiah
 
,; il.: pdf file
English

Sirkulasi

Rp. 0
Rp. 0
Tidak

Pengarang

FADRIANTO SULISTIYORAHMAN
Perorangan
Bedy Purnama, Edward Ferdian
 

Penerbit

Universitas Telkom, S1 Informatika
Bandung
2024

Koleksi

Kompetensi

  • CII3C3 - PEMBELAJARAN MESIN

Download / Flippingbook

 

Ulasan

Belum ada ulasan yang diberikan
anda harus sign-in untuk memberikan ulasan ke katalog ini