nerf
nerf copied to clipboard
bmild
Code release for NeRF (Neural Radiance Fields)
Hello, For the code in the single image part, I am confused about why only choose 1024 rays from one image, and it needs to repeat 1000,000 times. Are there...
Hi @bmild I am trying to calculate the gradient for the entire image instead of just a few sampled rays(= N_rand). Is it possible to do so? Seems like we...
Hi, I've studied the code and noticed the code applied some kind of formula to calculate "a reasonable focal depth" for a dataset when using LLFF. Is there a mathematical...
I want to experiment a little bit with NeRF but when I use my gtx970 I get the resource exhaust error (understandable). I can get a gtx1070 but I'm not...
I was running this on a cluster with a V100 GPU and 16 CPUs. It ran all the way through for the fern demo, but when we took our own...
WARNING:tensorflow:Entity could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`)...
Hi, According to Eq.(16)-(17) in the NDC [writeup](https://github.com/bmild/nerf/files/4451808/ndc_derivation.pdf) and implementation in [here](https://github.com/bmild/nerf/blob/20a91e764a28816ee2234fcadb73bd59a613a44c/run_nerf_helpers.py#L143), the Euclidean space to be converted to NDC space is chosen as the view frustum (or field of...
You said you can train a NeRF using only one GPU. I run your code by llff_config.txt on a Tesla V100 GPU with 16G memory. And it runs out of...
On the paper , it is mentioned that inference speed of NeRF is very slow. It seems to me that, to get an image, there are two stages. First, we...
Hi, how can I get the poses given that I have the 3D point clouds and 2D landmarks for every scene? Is it correct if I do camera calibration and...
