
Researchers have presented a new method of single-image 3D reconstruction, called One-2-3-45, which takes one picture of an object and generates a 360-degree 3D textured mesh in 45 seconds.
"We first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes."
The authors say their method reconstructs 3D shapes in less time than existing ones without expensive optimizations, favors better geometry, generates more consistent results, and adheres more closely to the input image.
It can also support text-to-3D workflows by integrating with text-to-image diffusion models.
Find out more about the project here and don't forget to join our 80 Level Talent platform and our Telegram channel, follow us on Instagram and Twitter, where we share breakdowns, the latest news, awesome artworks, and more.