Picture for Shubhajit Basak

Shubhajit Basak

LatentColorization: Latent Diffusion-Based Speaker Video Colorization

Add code
May 09, 2024
Viaarxiv icon

A lightweight 3D dense facial landmark estimation model from position map data

Add code
Aug 29, 2023
Figure 1 for A lightweight 3D dense facial landmark estimation model from position map data
Figure 2 for A lightweight 3D dense facial landmark estimation model from position map data
Figure 3 for A lightweight 3D dense facial landmark estimation model from position map data
Figure 4 for A lightweight 3D dense facial landmark estimation model from position map data
Viaarxiv icon

Speech Driven Video Editing via an Audio-Conditioned Diffusion Model

Add code
Jan 12, 2023
Figure 1 for Speech Driven Video Editing via an Audio-Conditioned Diffusion Model
Figure 2 for Speech Driven Video Editing via an Audio-Conditioned Diffusion Model
Figure 3 for Speech Driven Video Editing via an Audio-Conditioned Diffusion Model
Figure 4 for Speech Driven Video Editing via an Audio-Conditioned Diffusion Model
Viaarxiv icon

Methodology for Building Synthetic Datasets with Virtual Humans

Add code
Jun 21, 2020
Figure 1 for Methodology for Building Synthetic Datasets with Virtual Humans
Figure 2 for Methodology for Building Synthetic Datasets with Virtual Humans
Figure 3 for Methodology for Building Synthetic Datasets with Virtual Humans
Figure 4 for Methodology for Building Synthetic Datasets with Virtual Humans
Viaarxiv icon