[HN Gopher] Magic123: One Image to High-Quality 3D Object Genera... ___________________________________________________________________ Magic123: One Image to High-Quality 3D Object Generation Author : GaggiX Score : 40 points Date : 2023-08-03 20:34 UTC (2 hours ago) (HTM) web link (guochengqian.github.io) (TXT) w3m dump (guochengqian.github.io) | reidjs wrote: | Can I use this? | carbocation wrote: | The code is here, so it seems so: | https://github.com/guochengqian/Magic123 | | It looks like if you use the full pipeline, it takes 2.5 hours | for textual inversion, 40 minutes for coarse estimation, and 20 | minutes for fine estimation. For one image, on a 32G V100. | ugh123 wrote: | Amazing work! It was be interesting to create a 'spatial viewer' | that could navigate around the object, rather than just watching | the object rotate in front of you. If theres a background scene, | then the object of interest could be extracted and three- | dimensionalized, while keeping the background scene flat. Then | the viewer could move around the object while maintaining (at | least a flat version of) the background. ___________________________________________________________________ (page generated 2023-08-03 23:00 UTC)