Hack: Learning a parametric head and neck model for high-fidelity animation
Significant advancements have been made in developing parametric models for digital
humans, with various approaches concentrating on parts such as the human body, hand, or …
humans, with various approaches concentrating on parts such as the human body, hand, or …
A 3D model encryption method supporting adaptive visual effects after decryption
Abstract 3D model security protection has become increasingly essential due to its wide
engineering applications. Encryption is a common method to protect 3D models. Jansent et …
engineering applications. Encryption is a common method to protect 3D models. Jansent et …
Identity-Preserving Face Swapping via Dual Surrogate Generative Models
In this study, we revisit the fundamental setting of face-swapping models and reveal that only
using implicit supervision for training leads to the difficulty of advanced methods to preserve …
using implicit supervision for training leads to the difficulty of advanced methods to preserve …
A new neuroanatomical two-dimensional fitting three-dimensional imaging techniques in neuroanatomy education
X Shao, D Qiang, Q Yuan - BMC Medical Education, 2023 - Springer
Background Neuroanatomy is the most abstract and complex anatomy. Neurosurgeons
have to spend plenty of time mastering the nuances of the autopsy. However, the laboratory …
have to spend plenty of time mastering the nuances of the autopsy. However, the laboratory …
3D Reconstruction and Semantic Modeling of Eyelashes
High‐fidelity digital human modeling has become crucial in various applications, including
gaming, visual effects and virtual reality. Despite the significant impact of eyelashes on facial …
gaming, visual effects and virtual reality. Despite the significant impact of eyelashes on facial …
Deep shapely portraits
We present deep shapely portraits, a novel method based on deep learning, to automatically
reshape an input portrait to be better proportioned and more shapely while keeping …
reshape an input portrait to be better proportioned and more shapely while keeping …
球谐函数局部特征投影的三维人脸生成方法
赵世杰, 梁瑾裕, 杜晓飞, 高宏娟 - 计算机辅助设计与图形学学报 - jcad.cn
针对三维人脸生成任务中不能精确地控制局部属性生成的问题, 提出球谐函数局部特征投影的
三维人脸生成方法. 首先将三维人脸划分为多个属性, 每个属性对应多个潜变量; …
三维人脸生成方法. 首先将三维人脸划分为多个属性, 每个属性对应多个潜变量; …
Research on 2D Animation Simulation Based on Artificial Intelligence and Biomechanical Modeling
F Dai, Z Li - EAI Endorsed Transactions on Pervasive Health and …, 2024 - publications.eai.eu
Animation techniques have been completely transformed by the union of Artificial
Intelligence (AI) and biomechanical modeling, particularly in 2D animation. This study looks …
Intelligence (AI) and biomechanical modeling, particularly in 2D animation. This study looks …
Lip-Synchronized 3D Facial Animation Using Audio-Driven Graph Convolutional Autoencoder
The majority of state-of-the-art audio-driven facial animation methods implement a
differentiable rendering phase within their models, and as such, their output is a 2D raster …
differentiable rendering phase within their models, and as such, their output is a 2D raster …
Scalable Methods for Developing Interlocutor-aware Embodied Conversational Agents: Data Collection, Behavior Modeling, and Evaluation Methods
P Jonell - 2022 - diva-portal.org
This work presents several methods, tools, and experiments that contribute to the
development of interlocutor-aware Embodied Conversational Agents (ECAs). Interlocutor …
development of interlocutor-aware Embodied Conversational Agents (ECAs). Interlocutor …