-
Hi,
First of all, thank you for this amazing library!
Recently, I found a network configuration that seems to pose problems with input alignments. My network triggers a `tiny-cuda-nn/src/fully_fu…
-
HashGridSpatialIndex bin size defaults to about 500m in both X and Y directions. When linking, this means we may be scanning over a huge number of street geometries, perhaps 1-2 square km to find some…
abyrd updated
2 years ago
-
Hi,
I'm unable to run a really simple test, getting an illegal memory access error.
Here is the code sample:
```c++
{
const char *config = R"({"base_resolution":32,"log2_hashmap_size":16,"…
-
Hi, thanks for your wonderful work!
When running command to train monosdf, the following error is reported. I'm running it on Ubuntu 20.04 machine.
I have looked at issue #19 and command [the l…
-
I use WSL2 with ubuntu22.04.
I want to try the DLSS and I have installed Vulkan, but it still throws a waring like below.
```
huhao@DESKTOP-ICMSFQU:~/projects/instant-ngp$ ./build/testbed --sce…
-
I have built the great work NGP with and without GUI. It works fine in no-GUI version. But when I start a GUI version using
`./build-gui/testbed --scene=data/nerf/fox`
I get infos like
```10:24:04…
-
Hey, thank you for your great work!
I have tried on instant-ngp and it is beyond my expectation! So I want to export some images base on the model I trained on fox. I knew that in GUI we can set came…
-
I can only run the benchmark with the "OneBlob" encoding but not with the "HashGrid" encoding:
```
$ ./build/bench_image_ours data/images/albert.jpg data/config_hash.json
terminate called after …
-
Here are my logs when running the fox example in the testbed (After building successfully following the guidance [here](https://github.com/NVlabs/instant-ngp/discussions/205#discussioncomment-2224328)…
-
The hashgrid works on the assumption that each cell is twice as big as a particle's diameter so only 4 cells need to be considered in the neighbour search (see 'Fluid Engine Development' by Doyub Kim,…