Christoph Heindl

@yihao19 yes that's possible and demonstrated [here](https://github.com/cheind/pytorch-blender/tree/develop/examples/densityopt). It requires back-prop through non-differentiable render function of Blender, which I documented [there](https://github.com/cheind/pytorch-blender/blob/develop/examples/densityopt/etc/blendtorch_stochopt.pdf)

yes, that would be required, but it probably isn't. You might use one of the gradient estimator 'tricks' to avoid that - reparametrization or score function gradient estimation are keywords....

@vxgmichel just saw the pull-request and had to comment :) I believe `prefetch` is a better name than `buffer`, since for those comin from reactivex, `buffer` is already associated with...

Hi, very kewl project and thanks for letting me know! all the best chris rathaROG ***@***.***> schrieb am Do., 16. Okt. 2025, 23:16: > *rathaROG* created an issue (cheind/py-lapsolver#24) >...