{"id":19382887,"url":"https://github.com/locuslab/impsq","last_synced_at":"2025-10-06T00:47:38.745Z","repository":{"id":48092261,"uuid":"421520643","full_name":"locuslab/ImpSq","owner":"locuslab","description":"Implicit^2: Implicit model for implicit neural representations","archived":false,"fork":false,"pushed_at":"2021-11-24T19:53:37.000Z","size":343,"stargazers_count":28,"open_issues_count":2,"forks_count":6,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-04-23T20:47:53.131Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/locuslab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-10-26T17:25:32.000Z","updated_at":"2025-03-10T21:11:57.000Z","dependencies_parsed_at":"2022-08-12T18:30:43.605Z","dependency_job_id":null,"html_url":"https://github.com/locuslab/ImpSq","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/locuslab/ImpSq","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/locuslab%2FImpSq","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/locuslab%2FImpSq/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/locuslab%2FImpSq/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/locuslab%2FImpSq/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/locuslab","download_url":"https://codeload.github.com/locuslab/ImpSq/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/locuslab%2FImpSq/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278542683,"owners_count":26004061,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-05T02:00:06.059Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-10T09:23:44.709Z","updated_at":"2025-10-06T00:47:38.725Z","avatar_url":"https://github.com/locuslab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# (Implicit)\u003csup\u003e2\u003c/sup\u003e: Implicit Layers for Implicit Representations\n\nThis repo contains the implementation of the (Implicit)\u003csup\u003e2\u003c/sup\u003e network, an implicit neural representation (INR) learning framework backboned by [Deep Equilibrium Model](https://arxiv.org/abs/1909.01377) (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)\u003csup\u003e2\u003c/sup\u003e networks operate on significantly less computation and memory budget than exisiting explicit models while perform competitively.\n\n![Comparsion of explicit \u0026 implicit models](/assets/exp_vs_imp.png)\n\nFor more info and implementation details, please refer to [our paper](https://openreview.net/forum\\?id=AcoMwAU5c0s).\n\n## Data\n\nData used in this project is publicly available on Google Drive ([link](https://drive.google.com/drive/folders/1AVPQ_cqZTKedGWwJ0R39zSBQXw7LC6Pf?usp=sharing)).\n\nTo replicate our experiments, create a _data_ folder under the root directory and download the correponding datasets.\n\n```\n📦data \n┣ 📂image\n┃ ┣ 📜celeba_128_tiny.npy\n┃ ┣ 📜data_2d_text.npz\n┃ ┗ 📜data_div2k.npz\n┣ 📂3d_occupancy\n┣ 📂audio\n┣ 📂sdf\n┗ 📂video\n```\n\n## Reproduction of paper results\n\nTo reproduce results on image representation and image generalization, run\n\n```\npython scripts/train_2d_image.py --config_file ./configs/\u003ctask\u003e/config_\u003ctask\u003e_\u003cdataset\u003e.yaml\n```\n\nFor other experiments (audio, video, and 3d_occupancy), run \n```\npython scripts/train_\u003ctask\u003e.py --config_file ./configs/\u003ctask\u003e/\u003cmodel\u003e.yaml --dataset \u003cdataset\u003e\n```\n\nBelow is a list of available dataset options for each task (including some extra data we did not cover in the paper)\n```\naudio: ['bach', 'counting']\nvideo: ['cat', 'bikes']\n3d_occupancy: ['dragon', 'buddha', 'bunny', 'armadillo', 'lucy']\n```\n\n## Credits\n\n- The set of experiments on image, video, and audio signals and the corresponding data largely follows [SIREN](https://arxiv.org/abs/2006.09661) and [Fourier Feature Networks](https://arxiv.org/abs/2006.10739).\n- Models for the 3D occupancy experiments are directly retrieved from the [Stanford 3D Scanning Repository](http://graphics.stanford.edu/data/3Dscanrep/)\n\n## Citation\n```\n@inproceedings{huang2021impsq,\n  author    = {Zhichun Huang and Shaojie Bai and J. Zico Kolter},\n  title     = {(Implicit)^2: Implicit Layers for Implicit Representations},\n  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},\n  year      = {2021},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flocuslab%2Fimpsq","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flocuslab%2Fimpsq","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flocuslab%2Fimpsq/lists"}