{"id":19529268,"url":"https://github.com/isl-org/adaptive-surface-reconstruction","last_synced_at":"2025-08-08T14:24:40.813Z","repository":{"id":41314250,"uuid":"401614101","full_name":"isl-org/adaptive-surface-reconstruction","owner":"isl-org","description":"Adaptive Surface Reconstruction for 3D Data Processing","archived":false,"fork":false,"pushed_at":"2024-08-23T10:09:43.000Z","size":2023,"stargazers_count":50,"open_issues_count":2,"forks_count":8,"subscribers_count":9,"default_branch":"main","last_synced_at":"2024-08-23T11:27:55.595Z","etag":null,"topics":["3d","3d-reconstruction","pointcloud","pytorch","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/isl-org.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-08-31T07:35:00.000Z","updated_at":"2024-08-23T11:27:57.023Z","dependencies_parsed_at":"2024-08-20T07:58:13.773Z","dependency_job_id":null,"html_url":"https://github.com/isl-org/adaptive-surface-reconstruction","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2Fadaptive-surface-reconstruction","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2Fadaptive-surface-reconstruction/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2Fadaptive-surface-reconstruction/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2Fadaptive-surface-reconstruction/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/isl-org","download_url":"https://codeload.github.com/isl-org/adaptive-surface-reconstruction/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224033526,"owners_count":17244614,"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","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":["3d","3d-reconstruction","pointcloud","pytorch","tensorflow"],"created_at":"2024-11-11T01:23:12.216Z","updated_at":"2024-11-11T01:23:13.762Z","avatar_url":"https://github.com/isl-org.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Adaptive Surface Reconstruction\n\nThis repository contains code for the ICCV 2021 paper\n\n*B. Ummenhofer and V. Koltun. \"Adaptive Surface Reconstruction with Multiscale Convolutional Kernels\". ICCV 2021.*\n\n\nThe code implements our surface reconstruction, which can fuse large scale\npoint clouds to create surfaces with varying levels of details.\n\nIf you find this repository useful please cite our [paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Ummenhofer_Adaptive_Surface_Reconstruction_With_Multiscale_Convolutional_Kernels_ICCV_2021_paper.pdf).\n\n```\n@InProceedings{Ummenhofer_2021_ICCV,\n    author    = {Ummenhofer, Benjamin and Koltun, Vladlen},\n    title     = {Adaptive Surface Reconstruction With Multiscale Convolutional Kernels},\n    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},\n    month     = {October},\n    year      = {2021},\n    pages     = {5651-5660}\n}\n```\n\n\n## Dependencies\n\n## Packages for building the library\n- Pytorch 1.8.2 (can be installed with `python -m pip install torch==1.8.2+cpu -f https://download.pytorch.org/whl/lts/1.8/torch_lts.html`)\n- On Ubuntu the following packages are required: patchelf, xorg-dev, libglu1-mesa-dev, python3-dev\n  These can be installed with `apt install patchelf xorg-dev libglu1-mesa-dev python3-dev`\n\n## Packages required for training the network\n- Tensorflow 2.6.0\n- Open3D 0.14 or later with ML module (https://github.com/isl-org/Open3D/)\n- Tensorpack DataFlow (for reading data, ```pip install --upgrade git+https://github.com/tensorpack/dataflow.git```)\n- python-prctl (needed by Tensorpack DataFlow; depends on libcap-dev, install with ```apt install libcap-dev``` )\n- msgpack (```pip install msgpack``` )\n- msgpack-numpy (```pip install msgpack-numpy```)\n- python-zstandard (```pip install zstandard``` https://github.com/indygreg/python-zstandard)\n- SciPy\n\nThe versions match the configuration that we have tested on a system with Ubuntu 18.04.\nWe recommend using the latest versions for all packages.\n\n\n## Build instructions\n\nThe library, python bindings, and example binary can be build with\n\n```bash\nmkdir build\ncd build\ncmake ..\nmake\n```\n\nThe python package can be installed globally with the target ```pip-install-package```.\n```bash\n# inside the build directory\nmake install-pip-package\n```\n\nA portable AppImage of the binary can be created with the target ```appimage```.\nThis requires the linuxdeploy tool from https://github.com/linuxdeploy/linuxdeploy/releases/tag/continuous\n```bash\n# inside the build directory\n# creates appimage/asrtool-0.1.0-x86_64.AppImage inside the build directory\nmake appimage \n```\n\n\n## Directory structure\n\nThe project consists of a python module, a cpp library, an example binary, and training code.\nNote that the python module is required for the training code to work.\nThe following gives an overview of how the code is organized.\n```\n├─ appimage               # Scripts and resources for building an AppImage for the binary\n├─ cmake                  # CMake files for finding dependencies\n├─ cpp\n    ├─ bin                # Code for the example binary\n    ├─ lib                # Code and headers for the library\n    ├─ pybind             # Code for the python binding\n├─ models                 # Code for training the models\n├─ python                 # Python code and scripts for the python module\n├─ utils                  # Contains general utility scripts\n    ├─ deeplearningutils  # General training utils for tf/torch\n```\n\n## License\n\nCode and scripts are under the Apache-2.0 license.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fisl-org%2Fadaptive-surface-reconstruction","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fisl-org%2Fadaptive-surface-reconstruction","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fisl-org%2Fadaptive-surface-reconstruction/lists"}