no code implementations • 16 Dec 2024 • Hyeonchu Park, Byungjun Kim, Bugeun Kim
The experimental result shows that DART can discriminate multiple black-box LLMs without using syntactic features and knowing the origin of AIGT.
1 code implementation • 15 Dec 2024 • Byungjun Kim, Minju Kim, Dayeon Seo, Bugeun Kim
First, we define passive pricing as the limited ability of merchants to modify predefined item prices.
no code implementations • 19 Aug 2024 • Byungjun Kim, Dayeon Seo, Bugeun Kim
We conducted an experiment with four LLMs, analyzing their gameplay behavior in SpyGame both quantitatively and qualitatively.
no code implementations • CVPR 2024 • Inhee Lee, Byungjun Kim, Hanbyul Joo
In this paper, we present a method to reconstruct the world and multiple dynamic humans in 3D from a monocular video input.
no code implementations • CVPR 2024 • Hyunsoo Cha, Byungjun Kim, Hanbyul Joo
We present PEGASUS, a method for constructing a personalized generative 3D face avatar from monocular video sources.
no code implementations • CVPR 2024 • Taeksoo Kim, Byungjun Kim, Shunsuke Saito, Hanbyul Joo
Through a series of decomposition steps, we obtain multiple layers of 3D assets in a shared canonical space normalized in terms of poses and human shapes, hence supporting effortless composition to novel identities and reanimation with novel poses.
1 code implementation • ICCV 2023 • Byungjun Kim, Patrick Kwon, Kwangho Lee, Myunggi Lee, Sookwan Han, Daesik Kim, Hanbyul Joo
We propose a 3D generation pipeline that uses diffusion models to generate realistic human digital avatars.
no code implementations • 8 Aug 2022 • Gwangtak Bae, Byungjun Kim, Seongyong Ahn, Jihong Min, Inwook Shim
LiDAR is widely used to capture accurate 3D outdoor scene structures.