[Prior Research Team Yoo Hee-jo] Pose estimation is one of the visual processing technologies that tracks the movement of characters in a video. Body landmarks, which are similar to facial landmarks, are extracted and connected to describe the posture of the entire body. Most of…
[Service Development Team Byungin Kim] MetaHuman Creator is a digital human creation tool recently released by Epic Games. It looks similar to the character creation of an MMORPG game, but it is very difficult to implement such a real-time digital human, and it is a very time-consuming task. It is easy to rig, hair,...
Most decoration apps currently running on mobile phones such as Snow and Line Camera operate in the form of extracting facial landmarks and overlaying previously created objects. Also, in recent years, various image processing techniques such as beauty filters...
ImageNet is a dataset that has greatly influenced the advancement of AI technology so that no one knows about AI researchers. Consisting of a large number of images and their metadata, this dataset consists of approximately 14 million images...
As a deep learning-based image generation method, GAN produces a lot of amazing results. In particular, the latent space is simply random because it is possible to make changes that have a number of meaningful meanings by changing the latent vector after learning.
Tensorflow Lite is a software package that contains tools that allow AI models trained with Tensorflow to run on mobile devices. It is said to be running on over 4 billion devices now. Basically, the trained model is converted to Tensorflow Lite…
Avatarify is a program that adds real-time avatar animation functions to various video communication programs such as Zoom, Teams, Hangout, and Skype, and is open source. It is developed in the form of replacing the camera input of a video communication program, and the algorithm uses a first-order motion model.
The technology to create 3D models from a single photo has been unveiled under the name MeInGame. Looking at the results uploaded to the public repository, it is not yet enough to be applied to the service without the designer's work, but it will significantly reduce the initial modeling effort…
Since the advent of AlexNet consisting of multiple convolution layers, there have been many studies on the structure of deep learning models. For example, Google Inception uses convolution layers with different kernel sizes, such as 3×3, 5×5, and 7×7…
