[HN Gopher] Image Generation with Electrostatics
___________________________________________________________________
Image Generation with Electrostatics
Author : SleekEagle
Score : 36 points
Date : 2022-11-30 18:10 UTC (4 hours ago)
(HTM) web link (www.assemblyai.com)
(TXT) w3m dump (www.assemblyai.com)
| agumonkey wrote:
| Kinda reminds me of the recent morphogenesis studies shown on
| youtube (Levin and others).
| fxtentacle wrote:
| All the novelty appears to boil down to "this is a new sampler
| for diffusion-style models".
|
| Apparently, they are inspired by a different physical process.
| But that doesn't change the fact that they start with noise and
| then iteratively solve a differential equation to get to its end
| point. 2nd-order samplers like Heun already massively increased
| sampling speed over the original diffusion models, but sadly the
| article doesn't compare to that but merely to the original 1st-
| order samplers. So it might be that this one doesn't even create
| a speedup in practice.
|
| Does anyone else have more info on how this is different from
| "traditional" numerical differential-equation-based de-noising?
| thatcherc wrote:
| The big this seems to be that their noising/denoising process
| is invertible (to some extent) so it can be used to generate
| uncertainties, which is something the article says diffusion
| models can't do. The intuition is that the "flow" process used
| here is reversible (imagine going backwards in time and
| watching a cloud of charged particles coalescing into a bunch),
| which gives some nice properties that random blurring used in
| more common diffusion models does not.
|
| I think it's the reversible flow part that's important for the
| results, not the connection to the physical electrostatics
| system. It just happens to be that electrostatics have this
| nice flow behavior too and are a pretty approachable analogy
| for what the model's doing.
| fxtentacle wrote:
| I also noticed that they present it as if other diffusion
| models were not invertible, but they are. Also, they appear
| to be using DDPM++, the exact same neural network
| architecture as Stable Diffusion?
|
| Article says: "to train the neural network, which in this
| case is a U-Net (DDPM++ backbone)."
|
| Also it's kinda weird that they show videos generating images
| from noise (like Imagen / Stable Diffusion) but don't cite
| any recent diffusion paper.
|
| EDIT: In fact they don't cite ANY 2022 paper. So my guess
| would be that they submitted this last year and now it's been
| made public because now the NeurIPS 2022 conference is taking
| place. But most likely, the actual research here predates the
| Stable Diffusion release.
___________________________________________________________________
(page generated 2022-11-30 23:01 UTC)