Results 51 to 60 of about 7,762 (182)

3D Character Reconstruction from Hand‐drawn Model Sheets

Computer Graphics Forum, EarlyView.
Abstract Hand‐drawn model sheets are widely used in character design to define 3D shape and appearance through sparse multi‐view drawings. Reconstructing 3D characters from such sparse inputs has traditionally been challenging due to insufficient visual information.
Hyejeong Yoon, Wonjong Jang, Yoonha Hwang, Seungyong Lee   +3 more
wiley   +1 more source

EA-GAN: restoration of text in ancient Chinese books based on an example attention generative adversarial network

Heritage Science, 2023
Ancient Chinese books are of great significance to historical research and cultural inheritance. Unfortunately, many of these books have been damaged and corroded in the process of long-term transmission.
Zheng Wenjun, Su Benpeng, Feng Ruiqi, Peng Xihua, Chen Shanxiong   +4 more
doaj   +1 more source

DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification [PDF]

IEEE Transactions on Information Forensics and Security, 2018
MeshFace photos have been widely used in many Chinese business organizations to protect ID face photos from being misused. The occlusions incurred by random meshes severely degenerate the performance of face verification systems, which raises the MeshFace verification problem between MeshFace and daily photos.
Shu Zhang 0015, Ran He 0001, Zhenan Sun, Tieniu Tan   +3 more
openaire   +1 more source

PBR‐Inspired Controllable Diffusion for Image Generation

Computer Graphics Forum, EarlyView.
Abstract Despite recent advances in text‐to‐image generation, controlling geometric layout and PBR material properties in synthesized scenes remains challenging. We present a pipeline that first produces a G‐buffer (albedo, normals, depth, roughness, shading, and metallic) from a text prompt and then renders a final image through a PBR‐inspired branch ...
Bowen Xue, Giuseppe Claudio Guarnera, Shuang Zhao, Zahra Montazeri   +3 more
wiley   +1 more source

See4D: Pose‐Free 4D Generation via Auto‐Regressive Video Inpainting

Computer Graphics Forum, EarlyView.
Abstract Immersive applications call for synthesizing spatiotemporal 4D content from casual videos without costly 3D supervision. Existing video‐to‐4D methods typically rely on manually annotated camera poses, which are labor‐intensive and brittle for in‐the‐wild footage.
Dongyue Lu, Ao Liang, Tianxin Huang, Xiao Fu, Yuyang Zhao, Baorui Ma, Liang Pan, Wei Yin, Lingdong Kong, Wei Tsang Ooi, Ziwei Liu   +10 more
wiley   +1 more source

Image Inpainting Technique Based on Smart Terminal: A Case Study in CPS Ancient Image Data

IEEE Access, 2019
Cyber-physical system (CPS) can intelligently feel the interactive information between data and terminal. The combination of CPS data and intelligent terminal can make terminal devices communicate with each other, coordinate operation, and share ...
Yu Weng, Haiwen Zhou, Jian Wan
doaj   +1 more source

TreeON: Reconstructing 3D Tree Point Clouds from Orthophotos and Heightmaps

Computer Graphics Forum, EarlyView.
Abstract We present TreeON, a novel neural‐based framework for reconstructing detailed 3D tree point clouds from sparse top‐down geodata, using only a single orthophoto and its corresponding Digital Surface Model (DSM). Our method introduces a new training supervision strategy that combines both geometric supervision and a differentiable shadow and ...
Angeliki Grammatikaki, Johannes Eschner, Pedro Hermosilla, Oscar Argudo, Manuela Waldner   +4 more
wiley   +1 more source

M2UNet: A Segmentation-Guided GAN with Attention-Enhanced U²-Net for Face Unmasking

Mathematics
Face unmasking is a critical task in image restoration, as masks conceal essential facial features like the mouth, nose, and chin. Current inpainting methods often struggle with structural fidelity when handling large-area occlusions, leading to blurred ...
Mohamed Mahmoud, Mostafa Farouk Senussi, Mahmoud Abdalla, Mahmoud SalahEldin Kasem, Hyun-Soo Kang   +4 more
doaj   +1 more source

LeafFit: Plant Assets Creation from 3D Gaussian Splatting

Computer Graphics Forum, EarlyView.
Abstract We propose LeafFit, a pipeline that converts 3D Gaussian Splatting (3DGS) of individual plants into editable, instanced mesh assets. While 3DGS faithfully captures complex foliage, its high memory footprint and lack of mesh topology make it incompatible with traditional game production workflows. We address this by leveraging the repetition of
Chang Luo, Nobuyuki Umetani
wiley   +1 more source

A State-of-the-Art Review on Image Synthesis With Generative Adversarial Networks

IEEE Access, 2020
Generative Adversarial Networks (GANs) have achieved impressive results in various image synthesis tasks, and are becoming a hot topic in computer vision research because of the impressive performance they achieved in various applications. In this paper,
Lei Wang, Wei Chen, Wenjia Yang, Fangming Bi, Fei Richard Yu   +4 more
doaj   +1 more source