6 papers
HOPE: Hand-Object Pressure Estimation from Monocular Videos
Subin Jeon, Byungjun Kim, Hanbyul Joo
Estimating physical pressure from vision is essential for understanding contact-rich hand-object interaction. However, prior vision-based pressure estimation methods are largely li…
Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views
Mijin Yoo, In Cho, Subin Jeon +3
A 3D scene is understood through its objects, not the primitives that compose them. Yet feed-forward reconstruction methods output dense, unstructured sets of points or Gaussians,…
HRDexDB: A Paired Human-Robot Dataset for Cross-Embodiment Dexterous Grasping
Jongbin Lim, Taeyun Ha, Mingi Choi +4
We present HRDexDB, a paired cross-embodiment dexterous grasping dataset of high-fidelity dexterous grasping sequences featuring both human and diverse robotic hands. Unlike existi…
Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priors
Subin Jeon, In Cho, Junyoung Hong +2
Most existing 3D keypoint estimation methods rely on manual annotations or calibrated multi-view images, both of which are expensive to collect. This paper introduces KeyDiff3D, a…
ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors
Minsu Kim, Subin Jeon, In Cho +2
Recent advances in novel view synthesis (NVS) have enabled real-time rendering with 3D Gaussian Splatting (3DGS). However, existing methods struggle with artifacts and missing regi…
Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion Models
In Cho, Youngbeom Yoo, Subin Jeon +1
Constructing a compressed latent space through a variational autoencoder (VAE) is the key for efficient 3D diffusion models. This paper introduces COD-VAE that encodes 3D shapes in…