• Search by Module
• Search by Words
• Search Projects

• Java
• Python
• JavaScript
• TypeScript
• C++
• Scala
• Blog

Project: form2fit (GitHub Link)

• form2fit-master
  • LICENSE
  • setup.py
  • README.md
  • .gitignore
  • docs
    • setup.md
    • evaluate_benchmark.md
    • about_benchmark.md
    • paper_code.md
    • conventions.md
    • model_weights.md
  • form2fit
    • code
      • process_form2fit.py
      • ml
        • metrics.py
        • models
          • fcn.py
          • correspondence.py
          • resnet.py
          • suction.py
          • __init__.py
          • placement.py
          • base.py
        • dataloader
          • correspondence.py
          • suction.py
          • meta.py
          • __init__.py
          • placement.py
        • losses.py
        • __init__.py
      • utils
        • misc.py
        • sampling.py
        • ml.py
        • pointcloud.py
        • common.py
        • __init__.py
        • viz.py
      • gui
        • main.py
      • planner
        • __init__.py
        • planner.py
      • baseline
        • eval_baseline.py
      • __init__.py
      • eval_form2fit.py
    • download_data.sh
    • config.py
    • download_weights.sh
    • __init__.py
    • benchmark
      • eval.py
      • metrics.py
      • auc.py
  • assets

Form2Fit

Code for the paper

Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly
Kevin Zakka, Andy Zeng, Johnny Lee, Shuran Song
arxiv.org/abs/1910.13675
ICRA 2020

This repository contains:

• The Form2Fit Benchmark
  • Code to download and process the benchmark datasets.
  • Code to evaluate any model's performance on the benchmark test set.
• Code to reproduce the paper results:
  • Architectures, dataloaders and losses for suction, place and matching networks.
  • Planner module for intergrating all the outputs.
  • Baseline implementation.

If you find this code useful, consider citing our work:

@inproceedings{zakka2020form2fit,
  title={Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly},
  author={Zakka, Kevin and Zeng, Andy and Lee, Johnny and Song, Shuran},
  booktitle={Proceedings of the IEEE International Conference on Robotics and Automation},
  year={2020}
}

Documentation

• setup
• about the Form2Fit benchmark
• reproducing paper results
• evaluating a trained model
• model weights
• conventions

Todos

• [ ] Add processed generalization partition (combinations, mixtures and unseen) to benchmark.
• [ ] Add code for training the different networks.

Note

This is not an officially supported Google product.