tencentarc / hosnerf Goto Github PK

Thank you for releasing the code!
I'd like to train HOSNerf on the released dataset but I found no description about flow file format.
What is the correct flow file format & file name generated by RAFT?

Hello, I'm really interested in your research.
I want to train my custom video. But, I can't find the preprocessing code.
Could you offer the preprocessing code?
Thanks a lot

Hi, will you release the code of HOSNeRF ？

Hi, thank you for releasing the code!! This is an exciting project.

I'm wondering if there's an inference script which makes it easy to test this method? E.g. a script to process a video and output an artifact, and then a second script to use the artifact + camera position to output an image?

Also, apologies if this is documented somewhere, but roughly how long does the video processing take on an A100 or similar? And also rendering an image based on the processed video artifact?

Hi, thank you for the nice work.

I wonder if you can provide the trained checkpoints for the 6 sequences so we can run inference directly?

Hi,
Thanks for sharing your great paper and code.
I wish running your pre-trained checkpoint from: https://drive.google.com/drive/folders/15I7z7qjBL6rQ3z91_rzhR284L1vfxxOX
which step does this checkpoint belongs to? is it step 3 (3rd_Complete_HOSNeRF)?
can you please provide an example script for rendering a scene (preferbly with human+background) using your checkpoint?

I tried to modify the code of 3rd_Complete_HOSNeRF/run.py to load Backpack.cpkt checkpoint (not sure what I do is correct) but I am getting below error:
self._restore_modules_and_callbacks(ckpt_path)
File "/home/ofer/miniconda3/lib/python3.11/site-packages/pytorch_lightning/trainer/trainer.py", line 1142, in _restore_modules_and_callbacks
self._checkpoint_connector.restore_model()
File "/home/ofer/miniconda3/lib/python3.11/site-packages/pytorch_lightning/trainer/connectors/checkpoint_connector.py", line 179, in restore_model
self.trainer.strategy.load_model_state_dict(self._loaded_checkpoint)
File "/home/ofer/miniconda3/lib/python3.11/site-packages/pytorch_lightning/strategies/strategy.py", line 319, in load_model_state_dict
self.lightning_module.load_state_dict(checkpoint["state_dict"])
File "/home/ofer/miniconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 2153, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for LitMipNeRF360:
Unexpected key(s) in state_dict: "human.human_stateembeds.1", "human.human_stateembeds.2".
In call to configurable 'run' (<function run at 0x7f7f934b5bc0>)

can you please assist?

thanks alot,
Ofer