Pythonix Huang
Pythonix Huang
I use the script/compress_octree.py to compress the full resolution tree files, and use it in the web demo I build with emcmake. But it get stuck ![image](https://user-images.githubusercontent.com/16586180/124742218-130d9600-df4f-11eb-9efa-70eab63c6339.png) however, when I...
I got a question, if I want to use my own dataset, but there is no label in the dataset, when I construct the hdf5 file, what should I do...
Is there any pretrained model that you can provide?
I find the downscale_factor is automatically set to 2 when training on 1920*1080 images, I don't want that happen, how can I set the downscale_factor? I try `--pipeline.datamanager.dataparser.downscale_factor 1` but...
There's a recent research aiming to improve quality and robustness on nerf named robustnerf, at https://robustnerf.github.io/public/, it looks pretty straightforward to add this in nerfstudio
Hello, I saw a demo video in https://twitter.com/nerfstudioteam/status/1606400977934123008, looks pretty good, can you share how you train this model and capture the data, if available, can the data be provided?
Hello, I am wondering if there is any plan to upgrade nerfstudio, eg. nerfacto model. I see some recent research aiming to improve nerf's resolution like [4k_nerf](https://arxiv.org/pdf/2212.04701.pdf) and [AligNeRF](https://arxiv.org/pdf/2211.09682v1.pdf). Will...
I am curious that when I execute ns-render using a custom camera path or calculated path, nerfstudio will load the training data and eval data like in training, would that...
when there are many training images such as in large scene, most of the VRAM are used to store training data, use --data_on_cpu can help reduce VRAM and make it...
https://github.com/andfanilo/streamlit-drawable-canvas/issues/105