Same as many other instances of specialized ML models, their results look good generally, but completely fall apart under scrutiny. Remember GPT-3 blogpost writing?

Although, they are getting better years after years, so maybe we'll be out of the uncanny valley at some point ?

I have been recently looking at several "3d scanning" from monocular images/videos solutions and although they make for impressive demos I'm afraid they are a few years away from robust results.

On one hand you have traditional photogrammetry based on classical image descriptors (from the beginning of the 2000s). A nice open source solution is Meshroom [1]. I have very little experience as I have just tinkered a little but I would say they work OK with geometry of medium complexity and detailed textures. They fail horribly with untextured objects, like for example a candle. They are semi-automatic: you upload some photos and run the pipepiline but for best results it's easy to tweak as there are a lot of knobs to try.

On the other hand you have these deep learning research papers. A lot of them have Colab notebooks you can try yourself (which is awesome, thank you). They can give you these very nice demos for some kind of objects (the ones we have a lot of training data, like human bodies), but they are not truly general and sometimes will generate artifacts. There is some opportunity here if they are integrated in a semi-supervised workflow, like this [2].

Anyway, just curious and not an expert.

[1] https://alicevision.org/ [2] https://keentools.io/products/facebuilder-for-blender

What was the issue with GPT-3 & blog posts?

The generated text often seems okay if you're skimming, but if you think about what they're saying, it's rarely meaningful.

I don't think that really came as a surprise to anyone... nobody thought that gpt-3 was going to make sensible long-form narratives.

Yet, people do seem to think that DALL-E 2 is going to be able to make sensible "long-form" illustrations and paintings.

that kind of high-frequency detail is easy to lose in a model and/or from smoothing techniques

Does this also apply to hands? They look mangled in these examples.

We're probably lucky that they chose to model fully clothed subjects. Based on the smearing we see in some translated details like the fingers and examples of holes in skirts we could have some comically bad output.