Picture for Min-Jung Kim

Min-Jung Kim

Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling

Add code
Nov 27, 2024
Viaarxiv icon

SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars

Add code
Oct 15, 2024
Viaarxiv icon

TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models

Add code
Jul 12, 2024
Figure 1 for TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models
Figure 2 for TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models
Figure 3 for TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models
Figure 4 for TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models
Viaarxiv icon

VEGS: View Extrapolation of Urban Scenes in 3D Gaussian Splatting using Learned Priors

Add code
Jul 03, 2024
Viaarxiv icon

FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fields

Add code
Aug 07, 2023
Viaarxiv icon

VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation

Add code
Dec 08, 2021
Figure 1 for VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation
Figure 2 for VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation
Figure 3 for VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation
Figure 4 for VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation
Viaarxiv icon