Instant 3d human avatar generation using image diffusion models

N Kolotouros, T Alldieck, E Corona… - … on Computer Vision, 2024 - Springer
We present AvatarPopUp, a method for fast, high quality 3D human avatar generation from
different input modalities, such as images and text prompts and with control over the …

Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures

G Sun, R Dabral, H Zhu, P Fua, C Theobalt… - arxiv preprint arxiv …, 2024 - arxiv.org
Real-time free-view human rendering from sparse-view RGB inputs is a challenging task
due to the sensor scarcity and the tight time budget. To ensure efficiency, recent methods …

Single image, any face: Generalisable 3D face generation

W Wang, H Yang, J Kittler, X Zhu - arxiv preprint arxiv:2409.16990, 2024 - arxiv.org
The creation of 3D human face avatars from a single unconstrained image is a fundamental
task that underlies numerous real-world vision and graphics applications. Despite the …

Gen-3Diffusion: Realistic Image-to-3D Generation via 2D & 3D Diffusion Synergy

Y Xue, X **e, R Marin, G Pons-Moll - arxiv preprint arxiv:2412.06698, 2024 - arxiv.org
Creating realistic 3D objects and clothed avatars from a single RGB image is an attractive
yet challenging problem. Due to its ill-posed nature, recent works leverage powerful prior …