6 papers · 1 filter
ComPose: When to Trust Hands for Object Pose Tracking
Jisu Shin, Junoh Lee, JunGyu Lee +5
Reconstructing the motion of objects from videos is a key component for embodied AI and robot manipulation. While diverse approaches to object pose tracking have been studied, they…
Kinematics-Driven Gaussian Shape Deformation for Blurry Monocular Dynamic Scenes
Yeon-Ji Song, Kiyoung Kwon, Junoh Lee +2
Reconstructing dynamic 3D scenes from blurry monocular videos is challenging as motion-induced blur entangles object motion and geometry, hindering geometric consistency. We presen…
Relaxed Rigidity with Ray-based Grouping for Dynamic Gaussian Splatting
Junoh Lee, Junmyeong Lee, Yeon-Ji Song +4
The reconstruction of dynamic 3D scenes using 3D Gaussian Splatting has shown significant promise. A key challenge, however, remains in modeling realistic motion, as most methods f…
Continuous Locomotive Crowd Behavior Generation
Inhwan Bae, Junoh Lee, Hae-Gon Jeon
Modeling and reproducing crowd behaviors are important in various domains including psychology, robotics, transport engineering and virtual environments. Conventional methods have…
Fully Explicit Dynamic Gaussian Splatting
Junoh Lee, Chang-Yeon Won, Hyunjun Jung +2
3D Gaussian Splatting has shown fast and high-quality rendering results in static scenes by leveraging dense 3D prior and explicit representations. Unfortunately, the benefits of t…
Depth Prompting for Sensor-Agnostic Depth Estimation
Jin-Hwi Park, Chanhwi Jeong, Junoh Lee +1
Dense depth maps have been used as a key element of visual perception tasks. There have been tremendous efforts to enhance the depth quality, ranging from optimization-based to lea…