From CVPR: Reconstruct photorealistic 3D faces from a single "in-the-wild" imag

Deep Learning/Papers2read 2020. 5. 1. 15:19

From CVPR: Reconstruct photorealistic 3D faces from a single "in-the-wild" image with an increasing level of detail https://www.catalyzex.com/paper/arxiv:2003.13845

AvatarMe outperforms the existing arts by a significant margin and reconstructs authentic, 4K by 6K-resolution 3D faces from a single low-resolution image that, for the first time, bridges the uncanny valley.

'Deep Learning > Papers2read' 카테고리의 다른 글

오늘 소개드릴 논문은 흥미로운 응용사례와 같이 설명드리겠습니다. 최근에 보고있는 논문들이 ICLR이나 CVPR 최근 논문 + 실사례 적용을 하는 (0)	2020.05.15
This week's AI Paper Club topic is Deepfakes. We'll cover the technical, philoso (0)	2020.05.01
From CVPR '20: Robust 3D Self-portraits in Seconds https://www.catalyzex.com/pa (0)	2020.05.01
Softmax Splatting for Video Frame Interpolation (AI Short Paper Summary) Paper: (0)	2020.03.18
Handwritten word generation with GANs! https://www.profillic.com/paper/arxiv:20 (0)	2020.03.13