What's in your hands? 3D Reconstruction of Generic Objects in Hands

I know even publishing the code for stuff like this is generous but it'd be so cool if the standard practice included publishing a little wasm binary blob as a library independent network with weights to play with without having to go through colab. (Many frameworks have a way of creating that automatically already, e.g. torchscript or jax jit.)

Instead of working from a single 2D image as this work does, what is the state of the art for 3D reconstruction from multiple (non-calibrated) images? e.g. some casual shots of an object using my phone.

<p><pre><code> Dashcam threat sensors identified the suspect was holding a handgun-shaped object... </code></pre> -A press conference in the near future