김성빈

[김성빈 @sungbin052]

This is a joint work with #POSTECH and #KRAFTON

I would like to thank my advisor, Prof. Tae-Hyun Oh, and my wonderful collaborators, Hyun Lee, Da Hye, Suekyeong, and Janghoon!

[김성빈 @sungbin052]

Check out LaughTalk, our new #WACV2024 paper!
Project page: https://t.co/8YAWyPkdfP
Arxiv: https://t.co/ezQxTXCdXp

In this work, we propose a 3D talking head model, LaughTalk, that can simultaneously express speech🗣️ and laughter😀

[김성빈 @sungbin052]

Thus, we propose a novel task, dataset, and model to generate a 3D talking head capable of both articulate speech and authentic laughter.

[Arda Senocak @ardasnck]

Check out Sound2Scene, our new #CVPR2023 paper!

📄: https://t.co/8LHKZQ1sSY
🖥️: https://t.co/6P89qU8Vr7

We generate images from sounds 🎵 ➡️ 🏞️ Our model learned to synthesize images by simply watching Youtube videos, without any labels or language supervision.
🧵⬇️