Skip to content
/ ImpSq Public

Implicit^2: Implicit model for implicit neural representations

Notifications You must be signed in to change notification settings

locuslab/ImpSq

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

(Implicit)2: Implicit Layers for Implicit Representations

This repo contains the implementation of the (Implicit)2 network, an implicit neural representation (INR) learning framework backboned by Deep Equilibrium Model (DEQ). By taking advantage of the full-batch training scheme commonly applied to INR learning on low-dimensional data (e.g. images and audios) as well as an approximated gradient, (Implicit)2 networks operate on significantly less computation and memory budget than exisiting explicit models while perform competitively.

Comparsion of explicit & implicit models

For more info and implementation details, please refer to our paper.

Data

Data used in this project is publicly available on Google Drive (link).

To replicate our experiments, create a data folder under the root directory and download the correponding datasets.

📦data 
┣ 📂image
┃ ┣ 📜celeba_128_tiny.npy
┃ ┣ 📜data_2d_text.npz
┃ ┗ 📜data_div2k.npz
┣ 📂3d_occupancy
┣ 📂audio
┣ 📂sdf
┗ 📂video

Reproduction of paper results

To reproduce results on image representation and image generalization, run

python scripts/train_2d_image.py --config_file ./configs/<task>/config_<task>_<dataset>.yaml

For other experiments (audio, video, and 3d_occupancy), run

python scripts/train_<task>.py --config_file ./configs/<task>/<model>.yaml --dataset <dataset>

Below is a list of available dataset options for each task (including some extra data we did not cover in the paper)

audio: ['bach', 'counting']
video: ['cat', 'bikes']
3d_occupancy: ['dragon', 'buddha', 'bunny', 'armadillo', 'lucy']

Credits

Citation

@inproceedings{huang2021impsq,
  author    = {Zhichun Huang and Shaojie Bai and J. Zico Kolter},
  title     = {(Implicit)^2: Implicit Layers for Implicit Representations},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2021},
}

About

Implicit^2: Implicit model for implicit neural representations

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages