TensoRF bugfix: AABB normalized_positions to [-1, 1] #998
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Nice find. Does this change effect nerfacto / instant-ngp performance? |
|
I haven't checked if it affects their performance, since I was looking at TensoRF when I found this. Does the This is where it appears in nerfacto at least: |
JulianKnodt
force-pushed
the
normalize_bug_fix
branch
from
51a98db
to
026bdd8
Compare
|
I think hashgrid expects [0,1]. |
Previously, SceneBox.get_normalized_positions() returned a value in 0,1. This was fine for InstantNGP and Nerfacto, which use these values directly in an MLP. For TensoRF though, this was an error because grid sample expects values in the range [-1,1]. Thus, I think only 1/4th of the encoding planes were actually being used, and half of the encoding lines were.
JulianKnodt
force-pushed
the
normalize_bug_fix
branch
from
026bdd8
to
330195d
Compare
|
I've changed it to the TensoRF callsites, altho I browsed tcnn's readme, I didn't see a specific doc that referenced it anywhere but better to not cause random changes elsewhere. |
|
I just tested nerfacto with [-1,1] and it does work, but the results were worse. Lets just focus this PR on tensorf for now. |
ethanweber
approved these changes
Nov 21, 2022
ethanweber
changed the title
tancik
pushed a commit
to dozeri83/nerfstudio
that referenced
this pull request
Jan 20, 2023
AABB normalized_positions to [-1, 1] Previously, SceneBox.get_normalized_positions() returned a value in 0,1. This was fine for InstantNGP and Nerfacto, which use these values directly in an MLP. For TensoRF though, this was an error because grid sample expects values in the range [-1,1]. Thus, I think only 1/4th of the encoding planes were actually being used, and half of the encoding lines were.
chris838
pushed a commit
to chris838/nerfstudio
that referenced
this pull request
Apr 22, 2023
AABB normalized_positions to [-1, 1] Previously, SceneBox.get_normalized_positions() returned a value in 0,1. This was fine for InstantNGP and Nerfacto, which use these values directly in an MLP. For TensoRF though, this was an error because grid sample expects values in the range [-1,1]. Thus, I think only 1/4th of the encoding planes were actually being used, and half of the encoding lines were.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Previously, SceneBox.get_normalized_positions() returned a value in 0,1. This was fine for InstantNGP and Nerfacto, which use these values directly in an MLP. For TensoRF though, this was an error because grid sample expects values in the range
[-1,1]. Thus, I think only 1/4th of the encoding planes were actually being used, and half of the encoding lines were.