Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Cho, Kyusun"'
Autor:
Kim, Inès Hyeonsu, Lee, JoungBin, Jin, Woojeong, Son, Soowon, Cho, Kyusun, Seo, Junyoung, Kwak, Min-Seop, Cho, Seokju, Baek, JeongYeol, Lee, Byeongwon, Kim, Seungryong
Person re-identification (Re-ID) often faces challenges due to variations in human poses and camera viewpoints, which significantly affect the appearance of individuals across images. Existing datasets frequently lack diversity and scalability in the
Externí odkaz:
http://arxiv.org/abs/2406.16042
Autor:
Cho, Kyusun, Lee, Joungbin, Yoon, Heeji, Hong, Yeobin, Ko, Jaehoon, Ahn, Sangjun, Kim, Seungryong
We propose GaussianTalker, a novel framework for real-time generation of pose-controllable talking heads. It leverages the fast rendering capabilities of 3D Gaussian Splatting (3DGS) while addressing the challenges of directly controlling 3DGS with s
Externí odkaz:
http://arxiv.org/abs/2404.16012
Autor:
Ko, Jaehoon, Cho, Kyusun, Lee, Joungbin, Yoon, Heeji, Lee, Sangmin, Ahn, Sangjun, Kim, Seungryong
Recent methods for audio-driven talking head synthesis often optimize neural radiance fields (NeRF) on a monocular talking portrait video, leveraging its capability to render high-fidelity and 3D-consistent novel-view frames. However, they often stru
Externí odkaz:
http://arxiv.org/abs/2403.20153
With the recent advances in NeRF-based 3D aware GANs quality, projecting an image into the latent space of these 3D-aware GANs has a natural advantage over 2D GAN inversion: not only does it allow multi-view consistent editing of the projected image,
Externí odkaz:
http://arxiv.org/abs/2210.07301
We propose a novel framework for 3D-aware object manipulation, called Auto-Encoding Neural Radiance Fields (AE-NeRF). Our model, which is formulated in an auto-encoder architecture, extracts disentangled 3D attributes such as 3D shape, appearance, an
Externí odkaz:
http://arxiv.org/abs/2204.13426