Code Monkey home page Code Monkey logo

jchibane / box2mask Goto Github PK

View Code? Open in Web Editor NEW
51.0 51.0 6.0 3.44 MB

Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes

Python 75.31% CMake 0.04% Makefile 1.29% C++ 23.36%
3d-instance-segmentation 3d-scanning 3d-scene-understanding 3d-semantic-segmentation bounding-box bounding-box-annotations bounding-boxes box2mask instance-segmentation scene-understanding semantic-segmentation weakly-supervised-learning weakly-supervised-segmentation

box2mask's People

Contributors

anhtuanhsgs avatar jchibane avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar

box2mask's Issues

Missing function definition

Where is the definition of "get_sparse2dense()" called in method Evaluater.s3dis_eval() in file "models/evaluation.py"?

Missing gt_instance_data_txt folder can't evaluation

Hi, thanks for sharing this great work, I can't run evaluation during training because I don;t have the gt_instance_data_txt dir in scannet and seems the script utils/gt2eval.py is not working for me as well, could you give some instructions for that? thanks

Annotations for ARKitScenes dataset

Hi,
Thanks a lot for your great work. I am really interested in your predictions for the ARKitScenes dataset. Is it possible to release these annotations?

Pretrained for ArkitScenes3D

I would like to express my appreciation for your notable work in the field of weakly supervised 3D object instance segmentation (3DIS). Your contributions have been significant.
I am interested in reproducing the results you have achieved on ArkitScenes3D. However, it appears that, at present, only the ScannetV2 weights are available.
I eagerly anticipate your response and guidance in this matter.

Thank you for your time and assistance.
Sincerely,
PhucNDA.

The code might has memory leak

Hi, thanks for sharing this work, seems the training can't stand for several epoches, it can cause oom on a 48GB RAM machine even, seems the code would result in host memory leak

Windows support

First of all, congratulations for your great work. I currently use softgroup to perform instance detection and want to replace it with your work. I only need to make the inference with a 3d scene obtained by Bundlefusion. I am a windows user and have installed all the python packages with no problem. The only problem I have found is the use of MinkowskiEngine since it is not compatible with Windows. My question is if you know if I can make the Box2Mask method compatible with Windows, taking into account that I am only going to perform the inference of the model and that the MinkowskiEngine only works on Linux. Thanks for your attention

Pretrained model for ARKitScene dataset

Hi, thanks for this new approach in 3D instance segmentation. I'm interested in replicating your results for the ARKitScene dataset. Would you be able to release a pretrained model on the ARKitScene dataset? Thanks!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.