search

facebookresearch / robust-dynrf

An algorithm for reconstructing the radiance field of a dynamic scene from a casually-captured video.
MIT License
219 stars 11 forks source link

render a video of removing dynamic objects #7

Open liusang opened 1 year ago

liusang commented 1 year ago

Your job is great. After reading your code, I understand that it is possible to render a video of removing dynamic objects. Can it theoretically be implemented?

liusang commented 1 year ago

@alex04072000

alex04072000 commented 1 year ago

Hey @liusang , thank you for being interested in our work! Yes, you can achieve this by commenting out the loss calculations of the dynamic parts (also, the training will be faster). Specifically, comment out the code in L1112-1753 in train.py. Please give it a try and let me know if it works. Thank you!