3D Novel View Synthesis with Diffusion Models
3d-diffusion.github.io
3D Novel View Synthesis with Diffusion Models
1–10 of 14 posts
Re: 3D Novel View Synthesis with Diffusion Models
#2This approach is interesting in that it applies image-to-image diffusion modeling to autoregressively generate 3D consistent novel views, starting with even a single reference 2D image. Unlike some other approaches, a NeRF is not needed as an intermediate representation.
Re: 3D Novel View Synthesis with Diffusion Models
#3Soon to be the Face Back APP!
Re: 3D Novel View Synthesis with Diffusion Models
#4>> In order to maximize the reproducibility of our results, we provide code in JAX (Bradbury et al.,
2018) for our proposed X-UNet neural architecture from Section 2.3
Nice.
OpenAI shitting their pants even more.
Re: 3D Novel View Synthesis with Diffusion Models
#5It seems like this be used to create multiple views for fine tuning Stable Diffusion (textual inversion), from a single image.
Re: 3D Novel View Synthesis with Diffusion Models
#6Ok, NeRFs were a distraction then.
Re: 3D Novel View Synthesis with Diffusion Models
#7>> In order to maximize the reproducibility of our results, we provide code in JAX (Bradbury et al., 2018) for our proposed X-UNet neural architecture from Section 2.3 Nice. OpenAI shitting their pants even more.
Oh, OpenAI does more or less release that much. People don't have issues implementing the models from their papers.
What they don't do is release the actual models and datasets, and it's very expensive to retrain those.
Re: 3D Novel View Synthesis with Diffusion Models
#8Ok, NeRFs were a distraction then.
No, NeRFs are more interpretable because they directly model field densities which absorb and emit light. In this respect they are something akin to a neural version of photogrammetry. They don’t need to train on a large corpus of images, because they can reconstruct directly from a collection of posed images.
On the other hand, diffusion models can learn fairly arbitrary distributions of signals, so by exploiting this learned prior together with view consistency, they can be much more sample efficient than ordinary NeRFs. Without learning such a prior, 3D reconstruction from a single image is extremely ill-posed (much like monocular depth estimation).
Re: 3D Novel View Synthesis with Diffusion Models
#9I'm entirely unfamiliar with this, but is there a future where we can take a few pictures of something physical, and have AI generate a 3d model that we can then modify and 3d print?
Asking as someone who's dreadfully slow at 3d modeling.
Re: 3D Novel View Synthesis with Diffusion Models
#10I'm entirely unfamiliar with this, but is there a future where we can take a few pictures of something physical, and have AI generate a 3d model that we can then modify and 3d print? Asking as someone who's dreadfully slow at 3d modeling.
You're probably looking for multiview photogrammetry. Also known as "structure from motion." https://github.com/alicevision/Meshroom is a good free tool for this, but the most popular one is probably AGISoft MetaShape.