TensoRF
TensoRF copied to clipboard
evaluation_path rendering
Hello Chen,
It seems that in renderer.py for function evaluation_path() you are not covering ray sampling in the same way you do separately for blender.py and llff.py data loader (in blender.py you do not use ndc_rays_blender, while in llff you do).
I think some quick fix to make args.render_path=1 be able to work for both loaders would be to go from:
if ndc_ray:
to
if ndc_ray and 'blender' not in str(type(test_dataset)):
Hello, may I ask how you implemented “render_path for the Blender dataset?I really hope to receive your response and see the code you have modified.
I have opened this long time ago, so I don't recall whether I changed anything besides the line I've mentioned. What issue are you experiencing?
我很久以前就打开过这个,所以我不记得除了我提到的那一行之外我是否改变过任何东西。您遇到什么问题?
I want to implement a custom rendering path on the Blender dataset, like the 'get_spiral' function on the llff dataset, but my current test results are incorrect. May I ask how you can modify it
I think you should open a separate new Issue on here, and I can see if I can help
我认为你应该在这里单独开一个新问题,我看看是否可以提供帮助
好的 我创建了一个新的问题 https://github.com/apchenstu/TensoRF/issues/78