Anilkumar

> > More update: Actually these large values of indices are coming from func torchsearchsorted.searchsorted() > > inds = torchsearchsorted.searchsorted(cdf, u, side="right") --> after this line of code inds values...

But in original NeRF, they use view directions as zeros to extract a mesh. Could the same be used here?

I also have a similar problem, I would be interested to know the changes you made to loos function to avoid the black images

Hi @himanshu-daga Thanks for the response. If it makes sense, I think it would make the model biased or force the model to learn features from pixels that are non-zero....

@sxyu What is this bounding box sampling?

Same error for me too, did you manage to solve it?