{"id":13443084,"url":"https://github.com/ldkong1205/LaserMix","last_synced_at":"2025-03-20T15:33:35.117Z","repository":{"id":41804351,"uuid":"505766163","full_name":"ldkong1205/LaserMix","owner":"ldkong1205","description":"[CVPR 2023 Highlight] LaserMix for Semi-Supervised LiDAR Semantic Segmentation","archived":false,"fork":false,"pushed_at":"2024-05-14T03:39:28.000Z","size":9030,"stargazers_count":279,"open_issues_count":3,"forks_count":17,"subscribers_count":16,"default_branch":"main","last_synced_at":"2024-08-01T03:42:41.408Z","etag":null,"topics":["autonomous-driving","lidar","segmentation","semi-supervised-learning"],"latest_commit_sha":null,"homepage":"https://ldkong.com/LaserMix","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/ldkong1205.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-06-21T08:59:57.000Z","updated_at":"2024-07-22T01:37:02.000Z","dependencies_parsed_at":"2024-07-20T21:41:04.058Z","dependency_job_id":null,"html_url":"https://github.com/ldkong1205/LaserMix","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/ldkong1205%2FLaserMix","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ldkong1205%2FLaserMix/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ldkong1205%2FLaserMix/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ldkong1205%2FLaserMix/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ldkong1205","download_url":"https://codeload.github.com/ldkong1205/LaserMix/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221779815,"owners_count":16879012,"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":["autonomous-driving","lidar","segmentation","semi-supervised-learning"],"created_at":"2024-07-31T03:01:55.828Z","updated_at":"2024-10-28T04:30:19.905Z","avatar_url":"https://github.com/ldkong1205.png","language":"Python","funding_links":[],"categories":["Python","CV Downstream Tasks"],"sub_categories":["**Segmentation**"],"readme":"\u003cbr /\u003e\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/figs/logo.png\" align=\"center\" width=\"30%\"\u003e\n\n  \n  \u003ch3 align=\"center\"\u003e\u003cstrong\u003eLaserMix for Semi-Supervised LiDAR Semantic Segmentation\u003c/strong\u003e\u003c/h3\u003e\n  \n  \u003cp align=\"center\"\u003e\n      \u003ca href=\"https://scholar.google.com/citations?user=-j1j7TkAAAAJ\" target='_blank'\u003eLingdong Kong\u003c/a\u003e,\u0026nbsp;\n      \u003ca href=\"https://scholar.google.com/citations?user=YUKPVCoAAAAJ\" target='_blank'\u003eJiawei Ren\u003c/a\u003e,\u0026nbsp;\n      \u003ca href=\"https://scholar.google.com/citations?user=lSDISOcAAAAJ\" target='_blank'\u003eLiang Pan\u003c/a\u003e,\u0026nbsp;\n      \u003ca href=\"https://scholar.google.com/citations?user=lc45xlcAAAAJ\" target='_blank'\u003eZiwei Liu\u003c/a\u003e\n    \u003cbr\u003e\n  S-Lab, Nanyang Technological University\n  \u003c/p\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://arxiv.org/abs/2207.00026\" target='_blank'\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Paper-%F0%9F%93%83-yellow\"\u003e\n  \u003c/a\u003e\n  \n  \u003ca href=\"https://ldkong.com/LaserMix\" target='_blank'\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Project-%F0%9F%94%97-lightblue\"\u003e\n  \u003c/a\u003e\n  \n  \u003ca href=\"https://youtu.be/Xkwa5-dT0g4\" target='_blank'\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Demo-%F0%9F%8E%AC-yellow\"\u003e\n  \u003c/a\u003e\n  \n  \u003ca href=\"\" target='_blank'\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Poster-%F0%9F%93%83-lightblue\"\u003e\n  \u003c/a\u003e\n  \n  \u003ca href=\"https://zhuanlan.zhihu.com/p/528689803\" target='_blank'\u003e\n    \u003cimg src=\"https://img.shields.io/badge/%E4%B8%AD%E8%AF%91%E7%89%88-%F0%9F%90%BC-yellow\"\u003e\n  \u003c/a\u003e\n  \n  \u003ca href=\"\" target='_blank'\u003e\n    \u003cimg src=\"https://visitor-badge.laobi.icu/badge?page_id=ldkong1205.LaserMix\u0026left_color=gray\u0026right_color=lightblue\"\u003e\n  \u003c/a\u003e\n  \n\u003c/p\u003e\n\n## About\n\n\u003cstrong\u003eLaserMix\u003c/strong\u003e is a semi-supervised learning (SSL) framework designed for LiDAR semantic segmentation. It leverages the strong \u003cstrong\u003espatial prior\u003c/strong\u003e of driving scenes to construct \u003cstrong\u003elow-variation areas\u003c/strong\u003e via \u003cstrong\u003elaser beam mixing\u003c/strong\u003e, and encourages segmentation models to make \u003cstrong\u003econfident\u003c/strong\u003e and \u003cstrong\u003econsistent\u003c/strong\u003e predictions before and after mixing.\n\n\u003cbr\u003e\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/figs/laser.png\" align=\"center\" width=\"50%\"\u003e\n  \u003cbr\u003e\n  Fig. Illustration for laser beam partition based on inclination \u0026phi;.\n\u003c/p\u003e\n\u003cbr\u003e\n\nVisit our \u003ca href=\"https://ldkong.com/LaserMix\" target='_blank'\u003eproject page\u003c/a\u003e to explore more details. :red_car:\n\n\n## Updates\n\n- \\[2024.05\\] - Our improved framework, [LaserMix++](https://arxiv.org/abs/2405.05258) :rocket:, is avaliable on arXiv.\n- \\[2024.01\\] - The [toolkit](https://github.com/robodrive-24/toolkit) tailored for [The RoboDrive Challenge](https://robodrive-24.github.io/) has been released. :hammer_and_wrench:\n- \\[2023.12\\] - We are hosting [The RoboDrive Challenge](https://robodrive-24.github.io/) at [ICRA 2024](https://2024.ieee-icra.org/). :blue_car:\n- \\[2023.12\\] - Introducing [FRNet](https://github.com/Xiangxu-0103/FRNet), an efficient and effective **real-time** LiDAR segmentation model that achieves promising semi-supervised learning results on `SemanticKITTI` and `nuScenes`. Code and checkpoints are available for downloading.\n- \\[2023.03\\] - Intend to test the **robustness** of your LiDAR semantic segmentation models? Check our recent work, :robot: [Robo3D](https://github.com/ldkong1205/Robo3D), a comprehensive suite that enables OoD robustness evaluation of 3D segmentors on our newly established datasets: `SemanticKITTI-C`, `nuScenes-C`, and `WOD-C`.\n- \\[2023.03\\] - LaserMix was selected as a :sparkles: highlight :sparkles: at [CVPR 2023](https://cvpr.thecvf.com/) (top 10% of accepted papers).\n- \\[2023.02\\] - LaserMix was accepted to [CVPR 2023](https://cvpr.thecvf.com/)! :tada:\n- \\[2023.02\\] - LaserMix has been integrated into the [MMDetection3D](https://github.com/open-mmlab/mmdetection3d) codebase! Check [this](https://github.com/open-mmlab/mmdetection3d/pull/2302) PR in the `dev-1.x` branch to know more details. :beers:\n- \\[2023.01\\] - As suggested, we will establish a *sequential track* taking into account the LiDAR data collection nature in our semi-supervised LiDAR semantic segmentation benchmark. The results will be gradually updated in [RESULT.md](docs/RESULT.md).\n- \\[2022.12\\] - We support a wider range of LiDAR segmentation backbones, including [RangeNet++](https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/milioto2019iros.pdf), [SalsaNext](https://arxiv.org/abs/2003.03653), [FIDNet](https://arxiv.org/abs/2109.03787), [CENet](https://arxiv.org/abs/2207.12691), [MinkowskiUNet](https://github.com/NVIDIA/MinkowskiEngine), [Cylinder3D](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhu_Cylindrical_and_Asymmetrical_3D_Convolution_Networks_for_LiDAR_Segmentation_CVPR_2021_paper.pdf), and [SPVCNN](https://arxiv.org/pdf/2007.16100), under both fully- and semi-supervised settings. The checkpoints will be available soon!\n- \\[2022.12\\] - The derivation of spatial-prior-based SSL is available [here](https://ldkong.com/LaserMix/derivation.pdf). Take a look! :memo:\n- \\[2022.08\\] - LaserMix achieves 1st place among the semi-supervised semantic segmentation leaderboards of [nuScenes](https://paperswithcode.com/sota/semi-supervised-semantic-segmentation-on-25), [SemanticKITTI](https://paperswithcode.com/sota/semi-supervised-semantic-segmentation-on-24), and [ScribbleKITTI](https://paperswithcode.com/sota/semi-supervised-semantic-segmentation-on-23), based on [Paper-with-Code](https://paperswithcode.com/paper/lasermix-for-semi-supervised-lidar-semantic). :bar_chart:\n- \\[2022.08\\] - We provide a [video demo](https://youtu.be/Xkwa5-dT0g4) for visual comparisons on the SemanticKITTI val set. Take a look!\n- \\[2022.07\\] - Our paper is available on arXiv, click \u003ca href=\"https://arxiv.org/abs/2207.00026\" target='_blank'\u003ehere\u003c/a\u003e to check it out. Code will be available soon!\n\n\n## Outline\n\n- [Installation](#installation)\n- [Data Preparation](#data-preparation)\n- [Getting Started](#getting-started)\n- [Video Demo](#video-demo)\n- [Main Results](#main-results)\n- [TODO List](#todo-list)\n- [License](#license)\n- [Acknowledgement](#acknowledgement)\n- [Citation](#citation)\n\n## Installation\nPlease refer to [INSTALL.md](docs/INSTALL.md) for the installation details.\n\n\n## Data Preparation\nPlease refer to [DATA_PREPARE.md](docs/DATA_PREPARE.md) for the details to prepare the \u003csup\u003e1\u003c/sup\u003e[nuScenes](https://www.nuscenes.org), \u003csup\u003e2\u003c/sup\u003e[SemanticKITTI](http://www.semantic-kitti.org/), and \u003csup\u003e3\u003c/sup\u003e[ScribbleKITTI](https://github.com/ouenal/scribblekitti) datasets.\n\n\n## Getting Started\nPlease refer to [GET_STARTED.md](docs/GET_STARTED.md) to learn more usage about this codebase.\n\n\n## Video Demo\n| Demo 1 | Demo 2| Demo 3 | \n| :-: | :-: | :-: |\n| \u003cimg width=\"100%\" src=\"docs/figs/demo1.png\"\u003e |  \u003cimg width=\"100%\" src=\"docs/figs/demo2.png\"\u003e |  \u003cimg width=\"100%\" src=\"docs/figs/demo3.png\"\u003e | \n| [Link](https://youtu.be/Xkwa5-dT0g4) \u003csup\u003e:arrow_heading_up:\u003c/sup\u003e | [Link](https://youtu.be/OlKNDt8_um4) \u003csup\u003e:arrow_heading_up:\u003c/sup\u003e | [Link](https://youtu.be/f8UKgxi5mow) \u003csup\u003e:arrow_heading_up:\u003c/sup\u003e |\n\n\n## Main Result\n### Framework Overview\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/figs/framework.png\" align=\"center\" width=\"99.9%\"\u003e\n\u003c/p\u003e\n\n\n### Range View\n\n\u003ctable\u003e\n   \u003ctr\u003e\n      \u003cth rowspan=\"2\"\u003eMethod\u003c/th\u003e\n      \u003cth colspan=\"4\"\u003enuScenes\u003c/th\u003e\n      \u003cth colspan=\"4\"\u003eSemanticKITTI\u003c/th\u003e\n      \u003cth colspan=\"4\"\u003eScribbleKITTI\u003c/th\u003e\n   \u003c/tr\u003e\n   \u003ctr\u003e\n      \u003ctd\u003e1%\u003c/td\u003e \u003ctd\u003e10%\u003c/td\u003e \u003ctd\u003e20%\u003c/td\u003e \u003ctd\u003e50%\u003c/td\u003e\n      \u003ctd\u003e1%\u003c/td\u003e \u003ctd\u003e10%\u003c/td\u003e \u003ctd\u003e20%\u003c/td\u003e \u003ctd\u003e50%\u003c/td\u003e\n      \u003ctd\u003e1%\u003c/td\u003e \u003ctd\u003e10%\u003c/td\u003e \u003ctd\u003e20%\u003c/td\u003e \u003ctd\u003e50%\u003c/td\u003e\n   \u003c/tr\u003e\n   \u003ctr\u003e\n      \u003ctd\u003eSup.-only\u003c/td\u003e\n      \u003ctd\u003e38.3\u003c/td\u003e \u003ctd\u003e57.5\u003c/td\u003e \u003ctd\u003e62.7\u003c/td\u003e \u003ctd\u003e67.6\u003c/td\u003e\n      \u003ctd\u003e36.2\u003c/td\u003e \u003ctd\u003e52.2\u003c/td\u003e \u003ctd\u003e55.9\u003c/td\u003e \u003ctd\u003e57.2\u003c/td\u003e\n      \u003ctd\u003e33.1\u003c/td\u003e \u003ctd\u003e47.7\u003c/td\u003e \u003ctd\u003e49.9\u003c/td\u003e \u003ctd\u003e52.5\u003c/td\u003e\n   \u003c/tr\u003e\n   \u003ctr\u003e\n      \u003ctd\u003e\u003cstrong\u003eLaserMix\u003c/strong\u003e\u003c/td\u003e\n      \u003ctd\u003e49.5\u003c/td\u003e\u003ctd\u003e68.2\u003c/td\u003e\u003ctd\u003e70.6\u003c/td\u003e\u003ctd\u003e73.0\u003c/td\u003e\n      \u003ctd\u003e43.4\u003c/td\u003e\u003ctd\u003e58.8\u003c/td\u003e\u003ctd\u003e59.4\u003c/td\u003e\u003ctd\u003e61.4\u003c/td\u003e\n      \u003ctd\u003e38.3\u003c/td\u003e\u003ctd\u003e54.4\u003c/td\u003e\u003ctd\u003e55.6\u003c/td\u003e\u003ctd\u003e58.7\u003c/td\u003e\n   \u003c/tr\u003e\n  \u003ctr\u003e\n      \u003ctd\u003e\u003ci\u003eimprov.\u003c/i\u003e \u0026#8593\u003c/td\u003e\n      \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e11.2\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e10.7\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e7.9\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e5.4\u003c/td\u003e\n      \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e7.2\u003c/td\u003e  \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e6.6\u003c/td\u003e  \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e3.5\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e4.2\u003c/td\u003e\n      \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e5.2\u003c/td\u003e  \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e6.7\u003c/td\u003e  \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e5.7\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e6.2\u003c/td\u003e\n   \u003c/tr\u003e\n   \u003ctr\u003e\n      \u003ctd\u003e\u003cstrong\u003eLaserMix++\u003c/strong\u003e\u003c/td\u003e\n      \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e\n   \u003c/tr\u003e\n   \u003ctr\u003e\n      \u003ctd\u003e\u003ci\u003eimprov.\u003c/i\u003e \u0026#8593\u003c/td\u003e\n      \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e\n   \u003c/tr\u003e\n\u003c/table\u003e\n\n### Voxel\n\n\u003ctable\u003e\n   \u003ctr\u003e\n      \u003cth rowspan=\"2\"\u003eMethod\u003c/th\u003e\n      \u003cth colspan=\"4\"\u003enuScenes\u003c/th\u003e\n      \u003cth colspan=\"4\"\u003eSemanticKITTI\u003c/th\u003e\n      \u003cth colspan=\"4\"\u003eScribbleKITTI\u003c/th\u003e\n   \u003c/tr\u003e\n   \u003ctr\u003e\n      \u003ctd\u003e1%\u003c/td\u003e \u003ctd\u003e10%\u003c/td\u003e \u003ctd\u003e20%\u003c/td\u003e \u003ctd\u003e50%\u003c/td\u003e\n      \u003ctd\u003e1%\u003c/td\u003e \u003ctd\u003e10%\u003c/td\u003e \u003ctd\u003e20%\u003c/td\u003e \u003ctd\u003e50%\u003c/td\u003e\n      \u003ctd\u003e1%\u003c/td\u003e \u003ctd\u003e10%\u003c/td\u003e \u003ctd\u003e20%\u003c/td\u003e \u003ctd\u003e50%\u003c/td\u003e\n   \u003c/tr\u003e\n   \u003ctr\u003e\n      \u003ctd\u003eSup.-only\u003c/td\u003e\n      \u003ctd\u003e50.9\u003c/td\u003e \u003ctd\u003e65.9\u003c/td\u003e \u003ctd\u003e66.6\u003c/td\u003e \u003ctd\u003e71.2\u003c/td\u003e\n      \u003ctd\u003e45.4\u003c/td\u003e \u003ctd\u003e56.1\u003c/td\u003e \u003ctd\u003e57.8\u003c/td\u003e \u003ctd\u003e58.7\u003c/td\u003e\n      \u003ctd\u003e39.2\u003c/td\u003e \u003ctd\u003e48.0\u003c/td\u003e \u003ctd\u003e52.1\u003c/td\u003e \u003ctd\u003e53.8\u003c/td\u003e\n   \u003c/tr\u003e\n   \u003ctr\u003e\n      \u003ctd\u003e\u003cstrong\u003eLaserMix\u003c/strong\u003e\u003c/td\u003e\n      \u003ctd\u003e55.3\u003c/td\u003e \u003ctd\u003e69.9\u003c/td\u003e \u003ctd\u003e71.8\u003c/td\u003e \u003ctd\u003e73.2\u003c/td\u003e\n      \u003ctd\u003e50.6\u003c/td\u003e \u003ctd\u003e60.0\u003c/td\u003e \u003ctd\u003e61.9\u003c/td\u003e \u003ctd\u003e62.3\u003c/td\u003e\n      \u003ctd\u003e44.2\u003c/td\u003e \u003ctd\u003e53.7\u003c/td\u003e \u003ctd\u003e55.1\u003c/td\u003e \u003ctd\u003e56.8\u003c/td\u003e\n   \u003c/tr\u003e\n   \u003ctr\u003e\n      \u003ctd\u003e\u003ci\u003eimprov.\u003c/i\u003e \u0026#8593\u003c/td\u003e\n      \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e\u003csmall\u003e4.4\u003c/small\u003e\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e\u003csmall\u003e4.0\u003c/small\u003e\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e\u003csmall\u003e5.2\u003c/small\u003e\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e\u003csmall\u003e2.0\u003c/small\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e\u003csmall\u003e5.2\u003c/small\u003e\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e\u003csmall\u003e3.9\u003c/small\u003e\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e\u003csmall\u003e4.1\u003c/small\u003e\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e\u003csmall\u003e3.6\u003c/small\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e\u003csmall\u003e5.0\u003c/small\u003e\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e\u003csmall\u003e5.7\u003c/small\u003e\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e\u003csmall\u003e3.0\u003c/small\u003e\u003c/td\u003e \u003ctd\u003e\u003csup\u003e+\u003c/sup\u003e\u003csmall\u003e3.0\u003c/small\u003e\u003c/td\u003e\n   \u003c/tr\u003e\n   \u003ctr\u003e\n      \u003ctd\u003e\u003cstrong\u003eLaserMix++\u003c/strong\u003e\u003c/td\u003e\n      \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e\n   \u003c/tr\u003e\n   \u003ctr\u003e\n      \u003ctd\u003e\u003ci\u003eimprov.\u003c/i\u003e \u0026#8593\u003c/td\u003e\n      \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e \u003ctd\u003e \u003c/td\u003e\n   \u003c/tr\u003e\n\u003c/table\u003e\n\n### Ablation Studies\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/figs/ablation.png\" align=\"center\" width=\"99.9%\"\u003e\n\u003c/p\u003e\n\n### Qualitative Examples\n\n![qualitative](docs/figs/qualitative.png)\n\n### Checkpoints \u0026 More Results\n\nFor more experimental results and pretrained weights, please refer to [RESULT.md](docs/RESULT.md).\n\n\n## TODO List\n\n- [x] Initial release. :rocket:\n- [x] Add license. See [here](#license) for more details.\n- [x] Add video demos :movie_camera:\n- [x] Add installation details.\n- [x] Add data preparation details.\n- [ ] Add evaluation details.\n- [ ] Add training details.\n\n\n## Citation\n\nIf you find this work helpful, please kindly consider citing our paper:\n\n```bibtex\n@inproceedings{kong2023lasermix,\n  title = {LaserMix for Semi-Supervised LiDAR Semantic Segmentation},\n  author = {Kong, Lingdong and Ren, Jiawei and Pan, Liang and Liu, Ziwei},\n  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},\n  pages = {21705--21715},\n  year = {2023},\n}\n```\n\n\n## License\n\u003ca rel=\"license\" href=\"http://creativecommons.org/licenses/by-nc-sa/4.0/\"\u003e\u003cimg alt=\"Creative Commons License\" style=\"border-width:0\" src=\"https://i.creativecommons.org/l/by-nc-sa/4.0/80x15.png\" /\u003e\u003c/a\u003e\n\u003cbr /\u003e\nThis work is under the \u003ca rel=\"license\" href=\"http://creativecommons.org/licenses/by-nc-sa/4.0/\"\u003eCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License\u003c/a\u003e.\n\n\n## Acknowledgement\nThis work is developed based on the [MMDetection3D](https://github.com/open-mmlab/mmdetection3d) codebase.\n\n\u003e\u003cimg src=\"https://github.com/open-mmlab/mmdetection3d/blob/main/resources/mmdet3d-logo.png\" width=\"30%\"/\u003e\u003cbr\u003e\n\u003e MMDetection3D is an open-source toolbox based on PyTorch, towards the next-generation platform for general 3D perception. It is a part of the OpenMMLab project developed by MMLab.\n\nWe acknowledge the use of the following public resources during the course of this work: \u003csup\u003e1\u003c/sup\u003e[nuScenes](https://www.nuscenes.org), \u003csup\u003e2\u003c/sup\u003e[nuScenes-devkit](https://github.com/nutonomy/nuscenes-devkit), \u003csup\u003e3\u003c/sup\u003e[SemanticKITTI](http://www.semantic-kitti.org/), \u003csup\u003e4\u003c/sup\u003e[SemanticKITTI-API](https://github.com/PRBonn/semantic-kitti-api), \u003csup\u003e5\u003c/sup\u003e[ScribbleKITTI](https://github.com/ouenal/scribblekitti), \u003csup\u003e6\u003c/sup\u003e[FIDNet](https://github.com/placeforyiming/IROS21-FIDNet-SemanticKITTI), \u003csup\u003e7\u003c/sup\u003e[CENet](https://github.com/huixiancheng/CENet), \u003csup\u003e8\u003c/sup\u003e[SPVNAS](https://github.com/mit-han-lab/spvnas), \u003csup\u003e9\u003c/sup\u003e[Cylinder3D](https://github.com/xinge008/Cylinder3D), \u003csup\u003e10\u003c/sup\u003e[TorchSemiSeg](https://github.com/charlesCXK/TorchSemiSeg), \u003csup\u003e11\u003c/sup\u003e[MixUp](https://github.com/facebookresearch/mixup-cifar10), \u003csup\u003e12\u003c/sup\u003e[CutMix](https://github.com/clovaai/CutMix-PyTorch), \u003csup\u003e13\u003c/sup\u003e[CutMix-Seg](https://github.com/Britefury/cutmix-semisup-seg), \u003csup\u003e14\u003c/sup\u003e[CBST](https://github.com/yzou2/CBST), \u003csup\u003e15\u003c/sup\u003e[MeanTeacher](https://github.com/CuriousAI/mean-teacher), and \u003csup\u003e16\u003c/sup\u003e[Cityscapes](https://www.cityscapes-dataset.com).\n\nWe would like to thank \u003ca href=\"https://hongfz16.github.io/\" target='_blank'\u003eFangzhou Hong\u003c/a\u003e for the insightful discussions and feedback. ❤️\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fldkong1205%2FLaserMix","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fldkong1205%2FLaserMix","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fldkong1205%2FLaserMix/lists"}