microsoft / microsoft/TRELLIS

Why spconv instead of torchsparse++ or fvdb?

Open
#208 13 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13.7k
Forks
1.3k
PR merge metrics
No merged PRs in 30d

Description

Hello, first thanks for making this fantastic work available to everyone!
I can see it is using spconv for sparse convolution implementation.
As far as I know, torchsparse++ or fvdb may show better performance when compared to spconv.

I am curious whether the model can show better performance with adopting (seemingly) better sparse neural network libraries.

Any thoughts?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or entry points are identified. Start by locating the current spconv integration and defining comparable benchmarks against torchsparse++ and fvdb; done would require measured performance results and a clear decision on whether migration is warranted.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.