Code Monkey home page Code Monkey logo

mamba3d's Introduction

Mamba3D

PWC PWC PWC

This repository contains the official implementation of the paper:

Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model

  • We present Mamba3D, a state space model tailored for point cloud learning.
  • Mamba3D surpasses Transformer-based counterparts and concurrent works in multiple tasks, achieving multiple SoTA, with linear complexity.

📋 TODO

  • Release the training and evaluation code
  • Release the pretrained weights
  • Release the toy code on Colab

😊 Acknowledgement

We would like to thank the authors of Mamba, Vision Mamba, and Point-MAE for their great works and repos.

📚 Citation

If you find our work helpful, please consider citing:

@article{han2024mamba3d,
  title={Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model},
  author={Han, Xu and Tang, Yuan and Wang, Zhaoxuan and Li, Xianzhi},
  journal={arXiv preprint arXiv:2404.14966},
  year={2024}
}

mamba3d's People

Contributors

xhanxu avatar

Stargazers

avatar lan avatar xh avatar Yanran Zhang avatar avatar avatar avatar Guo Bingyang avatar avatar Zhifeng avatar LihuangFang avatar Kairun Wen avatar ShuaiLi avatar Yongsen Mao avatar Remco Leijenaar avatar Jie Wang avatar avatar Zhenchao Lin avatar Xiaobing Han avatar avatar avatar avatar avatar Tyler Rust avatar avatar avatar avatar Ruiyu Ming avatar avatar avatar avatar 夜阑仍有星 avatar avatar

Watchers

Ali Bahri avatar avatar avatar avatar

Forkers

whuhxb

mamba3d's Issues

Questions about LNP

About $\mathrm{F}_K\in\ \mathbb{R}\ ^{L\times\ k\times\ C}$,I'm not sure how it's obtained.
According to Eq. (5) $\mathbf{z^{\prime}}_\ell=\mathbf{LNP}(LN(\mathbf{z}_{\ell-1}+\mathbf{E}_{pos}))+\mathbf{z}_{\ell-1}$, LNP Input is $z_{\ell -1}+E_{pos}\in \mathbb{R} ^{\left( L+1 \right) \times C}$, but I don't know how to generate $\mathrm{F}_K$ from input.
The "k" in LNP is totally different from the "K" in Patch Embeddings. Did you use the second KNN here? I don't know how to generate $ L\times k\times C$ from $ \left( L+1 \right) \times C$.
Looking forward to your reply! Thank you!

Questions about biSSM

Hi, I read your paper and like your work. But I'm not sure if L+SSM and C-SSM are computed along the token dimension (L axis)?

关于预训练的提问

请问为什么你们的模型在未通过预训练的情况下在PB_T50_RS上能够达到91.81和92.64的成绩，却在经过MAE和BERT两种预训练策略之后却只能达到88.97和87.58了呢

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.