Giter VIP home page Giter VIP logo

3dlfm's Introduction

PWC PWC PWC

3D Lifting Foundation Model (3D-LFM) ๐ŸŒ

Welcome to the official repository for the 3D Lifting Foundation Model (3D-LFM), a model designed to lift 2D landmarks into high-fidelity 3D structures across diverse object categories. ๐Ÿš€

Current Status: This repository currently supports demo visualization of the model's performance. The comprehensive codebase, which includes actual training and evaluation functionalities, is planned for release as soon as the licensing information becomes available.

Features ๐ŸŒŸ

  • Versatile 3D Reconstruction: Capable of lifting single-view 2D landmarks into 3D structures for a wide range of objects.
  • OOD Handling: State-of-the-art performance on object-specific as well as object-agnostic Out-of-Distribution (OOD) validation data.
  • Interactive Visualization: Explore and visualize 3D predictions against ground truth data interactively.

Getting Started ๐Ÿš€

Prerequisites

  • Make sure you have Python installed on your system. You can download it from here.

Installation

  1. Clone the Repository:

    git clone https://github.com/mosamdabhi/3dlfm.git
    cd 3dlfm
  2. Set up a Virtual Environment (Optional but recommended):

    python -m venv venv
    source venv/bin/activate  # On Windows use `venv\Scripts\activate`

Running the Demo

Launch the demo_vis.ipynb notebook using Jupyter:

    jupyter notebook demo_vis.ipynb

Follow the instructions in the notebook for an interactive experience.

Usage ๐Ÿ“˜

After launching the notebook:

  • Choose a Category: Select from predefined categories for visualization (option to choose between standard validation and OOD validation).
  • Visualize Results: View the 3D reconstructed models and compare them with ground truth data (including actual RGB images).
  • Explore Different Objects: Experiment with various object categories, both standard and OOD.

Contributing ๐Ÿค

Contributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

  1. Fork the Project
  2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
  3. Commit your Changes (git commit -m 'Add some AmazingFeature')
  4. Push to the Branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

License ๐Ÿ“œ

Distributed under the BSD-3-Clause license. See LICENSE for more information.

Contact ๐Ÿ“ซ

3dlfm's People

Contributors

mosamdabhi avatar 3dlfm avatar

Stargazers

 avatar Jean-Philippe Deblonde avatar Alberto Remus avatar KimSeHyung avatar Pgxo20 avatar  avatar  avatar Ryota Tanaka avatar Fazeng Li avatar fang_chenfang avatar cjkangme avatar Kairun Wen avatar Shumpei Kobayashi avatar  avatar Jeff Carpenter avatar Nathan Litzinger avatar  avatar Simon Wengeler avatar ่ฐขๆ˜•่พฐ avatar  avatar Jonathan Clark avatar Antlitz.ai avatar Sai Kumar Dwivedi avatar Amir avatar Marcin avatar Dongwoo Ro avatar OldSix avatar coco avatar Chi Yan avatar Ravitej Bhagavathi avatar ็ˆฑๅฏๅฏ-็ˆฑ็”Ÿๆดป avatar Donald.Lee avatar Wooqy avatar  avatar David Marx avatar Mitchell Mosure avatar Doron Adler avatar Wei Wu avatar Peter Baylies avatar Zhang Qihang avatar  avatar  avatar  avatar Lu Ming avatar Zilong Chen avatar Jingnan Gao avatar kiui avatar

Watchers

Wei Wu avatar  avatar  avatar Simon Wengeler avatar  avatar Pyjcsx avatar Katsuya Hyodo avatar  avatar Rohit Lal avatar Amir avatar

3dlfm's Issues

How to handle face 3d landmark?

Thanks for your brilliant work! I want to test the face 3d landmark as showed in your paper. However the face category is not included in the demo. Could you please help me with that?

How to handle face 3d landmark?

Thanks for your brilliant work! I want to test the face 3d landmark as showed in your paper. However the face category is not included in the demo. Could you please help me with that?

About code

Awesome work! Will you release the code and the pretrained weight? When will you release them?

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.