{"id":13497348,"url":"https://github.com/uber-research/DeepPruner","last_synced_at":"2025-03-28T22:30:31.547Z","repository":{"id":43362991,"uuid":"215417096","full_name":"uber-research/DeepPruner","owner":"uber-research","description":"DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch (ICCV 2019)","archived":false,"fork":false,"pushed_at":"2020-09-05T08:17:08.000Z","size":20209,"stargazers_count":349,"open_issues_count":0,"forks_count":41,"subscribers_count":17,"default_branch":"master","last_synced_at":"2024-08-01T20:36:55.836Z","etag":null,"topics":["iccv2019","patchmatch","pytorch","real-time","stereo-matching","stereo-vision"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/uber-research.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":null,"support":null}},"created_at":"2019-10-15T23:48:59.000Z","updated_at":"2024-07-21T15:04:41.000Z","dependencies_parsed_at":"2022-09-11T16:31:59.006Z","dependency_job_id":null,"html_url":"https://github.com/uber-research/DeepPruner","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uber-research%2FDeepPruner","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uber-research%2FDeepPruner/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uber-research%2FDeepPruner/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uber-research%2FDeepPruner/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/uber-research","download_url":"https://codeload.github.com/uber-research/DeepPruner/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222418056,"owners_count":16981262,"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":["iccv2019","patchmatch","pytorch","real-time","stereo-matching","stereo-vision"],"created_at":"2024-07-31T20:00:29.321Z","updated_at":"2024-10-31T13:31:33.612Z","avatar_url":"https://github.com/uber-research.png","language":"Python","readme":"# DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch\n\nThis repository releases code for our paper [DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch](https://arxiv.org/abs/1909.05845).\n\n##### Table of Contents  \n[DeepPruner](#DeepPruner)  \n[Differentiable Patch Match](#DifferentiablePatchMatch)  \n[Requirements (Major Dependencies)](#Requirements)  \n[Citation](#Citation)  \n\n\n  \u003ca name=\"DeepPruner\"\u003e\u003c/a\u003e\n  ###  **DeepPruner** \n\n + An efficient \"Real Time Stereo Matching\" algorithm, which takes as input 2 images and outputs a disparity (or depth) map.\n\t\n\t\n\t\n\t![](readme_images/DeepPruner.png)\n\t\n\t\n\t\n + Results/ Metrics:\n\t\t\t\t\t\t\t\n    + [**KITTI**](http://www.cvlibs.net/datasets/kitti/eval_scene_flow.php?benchmark=stereo): **Results competitive to SOTA, while being real-time (8x faster than SOTA). SOTA among published real-time algorithms**.\n\t\n    \n    ![](readme_images/KITTI_test_set.png)\n\t  ![](readme_images/CRP.png)\n    ![](readme_images/uncertainty_vis.png)\n\t\n\t\n\t  + [**ETH3D**](https://www.eth3d.net/low_res_two_view?mask=all\u0026metric=bad-2-0): **SOTA among all ROB entries**. \n\t  \n    + **SceneFlow**: **2nd among all published algorithms, while being 8x faster than the 1st.**\n\t  \n    \u003cp align=\"center\"\u003e\n    \u003cimg src=\"readme_images/sceneflow.png\" width=\"60%\" /\u003e\n\t  \u003c/p\u003e \n         \n    \n\t\n\t  + [**Robust Vision Challenge**](http://www.robustvision.net/index.php): **Overall ranking 1st**. \n\t   \n    \u003cp align=\"center\"\u003e\n    \u003cimg src=\"readme_images/rob.png\" width=\"60%\" /\u003e\n\t  \u003c/p\u003e\n\t\n\t+ Runtime: **62ms** (for DeepPruner-fast), **180ms** (for DeepPruner-best)\n\t  \n\t+ Cuda Memory Requirements: **805MB** (for DeepPruner-best)\n\n\n\n  \u003ca name=\"DifferentiablePatchMatch\"\u003e\u003c/a\u003e\n  ### **Differentiable Patch Match**\n  + Fast algorithm for finding dense nearest neighbor correspondences between patches of images regions. \n    Differentiable version of the generalized Patch Match algorithm. ([Barnes et al.](https://gfx.cs.princeton.edu/pubs/Barnes_2010_TGP/index.php))\n    \n   \u003cp\u003e\n   \u003cimg src=\"readme_images/DPM.png\" width=\"50%\" /\u003e \u003cimg src=\"readme_images/DPM_filters.png\" width=\"40%\" /\u003e\n    \u003c/p\u003e\n\nMore details in the corresponding folder README.\n\n\n\u003ca name=\"Requirements\"\u003e\u003c/a\u003e\n## Requirements (Major Dependencies)\n+ Pytorch (0.4.1+)\n+ Python2.7\n+ torchvision (0.2.0+)\n\n\n\n\u003ca name=\"Citation\"\u003e\u003c/a\u003e\n## Citation\n\nIf you use our source code, or our paper, please consider citing the following:\n\u003e @inproceedings{Duggal2019ICCV,  \ntitle = {DeepPruner: Learning Efficient Stereo Matching  via Differentiable PatchMatch},  \nauthor = {Shivam Duggal and Shenlong Wang and Wei-Chiu Ma and Rui Hu and Raquel Urtasun},  \nbooktitle = {ICCV},  \nyear = {2019}\n}\n\nCorrespondences to Shivam Duggal \u003cshivamduggal.9507@gmail.com\u003e, Shenlong Wang \u003cslwang@cs.toronto.edu\u003e, Wei-Chiu Ma \u003cweichium@mit.edu\u003e\n","funding_links":[],"categories":["3DVision"],"sub_categories":["Depth/StereoMatching"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fuber-research%2FDeepPruner","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fuber-research%2FDeepPruner","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fuber-research%2FDeepPruner/lists"}