nsff_pl
nsff_pl copied to clipboard
kwea123
Neural Scene Flow Fields using pytorch-lightning, with potential improvements
Hello, I have been trying to train a model on Jumping sequence using your code but I have this cuda kernel error: ``` python train.py --dataset_name monocular --root_dir $ROOT_DIR --img_wh...
If I'd like to make a 360° capture of my dog, which wouldn't stay quiet during capture. Could this help me to get a Radiance Field I can later export...
To reproduce, pick a large batch_size and run with hard_sampling. Eventually it will throw `RuntimeError: CUDA out of memory`
I am not very clear about one point, and I really need your help. What's the differences between the mean of '_static_weights' and 'static_weights', take it a step further, why...
In test.ipynb, three keys of the results dict is not right. I found out the right ones and fixed them.
Hello @kwea123 I'm wondering why my reproduction is so bad, can you help explain it?  
I changed the default parameters num_gpus-->8\num_nodes-->8, and keep other default parameters unchanged, then run the train.py with 8_v100, but it always stuck on the device initialization and can't go on...
Hello author, thank you very much for such a good job. I have a request to ask you. One of my papers was reworked, and a reviewer asked me to...
 训练时psnr达到30，照理来说应该是成功了。但evaluate出来很奇怪，这个gif是训练视角
Nice work! In the part of the motion mask in the readme, you mentioned that flow-base masks are too noisy. I also have the same feeling when using the code...
