Cascade-zero123: One image to highly consistent 3d with self-prompted nearby views
Synthesizing multi-view 3D from one single image is a significant but challenging task. Zero-
1-to-3 methods have achieved great success by lifting a 2D latent diffusion model to the 3D …
1-to-3 methods have achieved great success by lifting a 2D latent diffusion model to the 3D …
MOSS: Motion-based 3D Clothed Human Synthesis from Monocular Video
H Wang, X Cai, X Sun, J Yue, Z Tang, S Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Single-view clothed human reconstruction holds a central position in virtual reality
applications, especially in contexts involving intricate human motions. It presents notable …
applications, especially in contexts involving intricate human motions. It presents notable …
StepIdeator: Utilizing Mixed Representations to Support Step-by-step Design With Generative AI
In product conceptual design, designers utilize multiple design representations to iteratively
ideate, externalize, and refine concepts. Mixed representations, defined as the simultaneous …
ideate, externalize, and refine concepts. Mixed representations, defined as the simultaneous …