3 papers
cs.CV2024
Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses
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. As a key idea, we represent both the world and multiple…
cs.CV2024
PEGASUS: Personalized Generative 3D Avatars with Composable Attributes
Hyunsoo Cha, Byungjun Kim, Hanbyul Joo
We present PEGASUS, a method for constructing a personalized generative 3D face avatar from monocular video sources. Our generative 3D avatar enables disentangled controls to selec…
cs.CV2022
SLiDE: Self-supervised LiDAR De-snowing through Reconstruction Difficulty
Gwangtak Bae, Byungjun Kim, Seongyong Ahn +2
LiDAR is widely used to capture accurate 3D outdoor scene structures. However, LiDAR produces many undesirable noise points in snowy weather, which hamper analyzing meaningful 3D s…