Reconstruction of machine-made shapes from bitmap sketches

I Puhachov, C Martens, PG Kry… - ACM Transactions on …, 2023 - dl.acm.org
We propose a method of reconstructing 3D machine-made shapes from bitmap sketches by
separating an input image into individual patches and jointly optimizing their geometry. We …

Polarized Object Surface Reconstruction Algorithm Based on RU-GAN Network

X Yang, C Cheng, J Duan, YF Hao, Y Zhu, H Zhang - Sensors, 2023 - mdpi.com
There are six possible solutions for the surface normal vectors obtained from polarization
information during 3D reconstruction. To resolve the ambiguity of surface normal vectors …

Automatic Illumination of Flat-Colored Drawings by 3D Augmentation of 2D Silhouettes

D Tschumperlé, C Porquet… - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
In this paper, a new automatic method for the illumination of flat-colored drawings is
proposed. First, we reconstruct a 3D augmentation of a 2D silhouette from the analysis of its …

ShadowGAN for Line Drawings Shadow Generation

H Xue, C Kang - International Conference on Artificial Neural Networks, 2023 - Springer
Shadow performs an important role in the image, which can enhance the image effect and
convey important visual clues. We propose a method based on deep learning to …

[PDF][PDF] Hand-drawn Illustration Design in National Wave Style Based on Deep Learning and Image Super Resolution Reconstruction

M Yu, SSB Jamali, AB Husain - Scalable Computing: Practice and …, 2024 - scpe.org
This research presents a novel framework, Deep Learning based Super Resolution
Reconstruction (DESRR), for the creation of hand-drawn illustrations in a specific National …

Computer-aided design of hand-drawn art food packaging design based on a deep neural network model

H Cui - … Journal for Simulation and Multidisciplinary Design …, 2024 - ijsmdo.org
Background: The term “hand-drawn art food packaging design”(HAFPD) refers to a novel
and creative method of food package design that makes use of hand-drawn illustrations …

[引用][C] Exploration of Deep Learning Techniques for Natural I age Matting

S Lutz - 2021