Experimental: Add initial wavefront/obj parser for vertices #1315
Conversation
This file contains hidden or 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
|
do you have any introduction to wavefront format? Can you link it in the PR given it's a less known format. |
yongtang
force-pushed
the
tinyobjloader
branch
from
2cec527 to
215f277
Compare
|
@burgerkingeater obj file is a simple ASCII format for 3D models (http://paulbourke.net/dataformats/obj/). I have updated the PR with additional description. Please take a look. |
kvignesh1420
reviewed
Mar 4, 2021
kvignesh1420
requested changes
Mar 4, 2021
There was a problem hiding this comment.
@yongtang thanks for adding the support for the wavefront .obj file format. Please check the minor docstring change.
This PR is an early experimental implementation of wavefront obj parser in tensorflow-io for 3D objects. This PR is the first step to obtain raw vertices in float32 tensor with shape of `[n, 3]`. Additional follow up PRs will be needed to handle meshs with different shapes (not sure if ragged tensor will be a good fit in that case) Some background on obj file: Wavefront (obj) is a format widely used in 3D (another is ply) modeling (http://paulbourke.net/dataformats/obj/). It is simple (ASCII) with good support for many softwares. Machine learning in 3D has been an active field with some advances such as PolyGen (https://arxiv.org/abs/2002.10880) Processing obj files are needed to process 3D with tensorflow. In 3D the basic elements could be vertices or faces. This PR tries to cover vertices first so that vertices in obj file can be loaded into TF's graph for further processing within graph pipeline. Signed-off-by: Yong Tang <[email protected]>
|
@kvignesh1420 Thanks for the review. The PR has been updated. Please take a look. |
michaelbanfield
pushed a commit
to michaelbanfield/io
that referenced
this pull request
Mar 30, 2021
…ow#1315) This PR is an early experimental implementation of wavefront obj parser in tensorflow-io for 3D objects. This PR is the first step to obtain raw vertices in float32 tensor with shape of `[n, 3]`. Additional follow up PRs will be needed to handle meshs with different shapes (not sure if ragged tensor will be a good fit in that case) Some background on obj file: Wavefront (obj) is a format widely used in 3D (another is ply) modeling (http://paulbourke.net/dataformats/obj/). It is simple (ASCII) with good support for many softwares. Machine learning in 3D has been an active field with some advances such as PolyGen (https://arxiv.org/abs/2002.10880) Processing obj files are needed to process 3D with tensorflow. In 3D the basic elements could be vertices or faces. This PR tries to cover vertices first so that vertices in obj file can be loaded into TF's graph for further processing within graph pipeline. Signed-off-by: Yong Tang <[email protected]>
zheolong
pushed a commit
to zheolong/io-1
that referenced
this pull request
Jul 24, 2025
…ow#1315) This PR is an early experimental implementation of wavefront obj parser in tensorflow-io for 3D objects. This PR is the first step to obtain raw vertices in float32 tensor with shape of `[n, 3]`. Additional follow up PRs will be needed to handle meshs with different shapes (not sure if ragged tensor will be a good fit in that case) Some background on obj file: Wavefront (obj) is a format widely used in 3D (another is ply) modeling (http://paulbourke.net/dataformats/obj/). It is simple (ASCII) with good support for many softwares. Machine learning in 3D has been an active field with some advances such as PolyGen (https://arxiv.org/abs/2002.10880) Processing obj files are needed to process 3D with tensorflow. In 3D the basic elements could be vertices or faces. This PR tries to cover vertices first so that vertices in obj file can be loaded into TF's graph for further processing within graph pipeline. Signed-off-by: Yong Tang <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
This PR is an early experimental implementation of wavefront obj
parser in tensorflow-io for 3D objects.
This PR is the first step to obtain raw vertices in float32
tensor with shape of
[n, 3].Additional follow up PRs will be needed to handle meshs with
different shapes (not sure if ragged tensor will be a good fit
in that case)
Some background on obj file:
Wavefront (obj) is a format widely used in 3D (another is ply)
modeling (http://paulbourke.net/dataformats/obj/). It is simple
(ASCII) with good support for many softwares. Machine learning
in 3D has been an active field with some advances such as
PolyGen (https://arxiv.org/abs/2002.10880)
Processing obj files are needed to process 3D with tensorflow.
In 3D the basic elements could be vertices or faces. This PR
tries to cover vertices first so that vertices in obj file
can be loaded into TF's graph for further processing within
graph pipeline.
Signed-off-by: Yong Tang [email protected]