{"id":26648502,"url":"https://github.com/KwanWaiPang/Awesome-Learning-based-VO-VIO","last_synced_at":"2025-03-25T00:02:12.773Z","repository":{"id":282221394,"uuid":"947868414","full_name":"KwanWaiPang/Awesome-Learning-based-VO-VIO","owner":"KwanWaiPang","description":"Paper Survey for Deep Visual (-Inertial) Odometry","archived":false,"fork":false,"pushed_at":"2025-03-22T09:09:36.000Z","size":1497,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-22T10:20:19.000Z","etag":null,"topics":["awesome","deep-learning","slam","vio","visual-odometry"],"latest_commit_sha":null,"homepage":"","language":null,"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/KwanWaiPang.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-03-13T11:25:50.000Z","updated_at":"2025-03-22T09:09:39.000Z","dependencies_parsed_at":"2025-03-13T12:42:35.487Z","dependency_job_id":null,"html_url":"https://github.com/KwanWaiPang/Awesome-Learning-based-VO-VIO","commit_stats":null,"previous_names":["kwanwaipang/awesome-learning-based-vo-vio"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KwanWaiPang%2FAwesome-Learning-based-VO-VIO","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KwanWaiPang%2FAwesome-Learning-based-VO-VIO/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KwanWaiPang%2FAwesome-Learning-based-VO-VIO/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KwanWaiPang%2FAwesome-Learning-based-VO-VIO/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/KwanWaiPang","download_url":"https://codeload.github.com/KwanWaiPang/Awesome-Learning-based-VO-VIO/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245372380,"owners_count":20604491,"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":["awesome","deep-learning","slam","vio","visual-odometry"],"created_at":"2025-03-25T00:02:02.388Z","updated_at":"2025-03-25T00:02:12.759Z","avatar_url":"https://github.com/KwanWaiPang.png","language":null,"funding_links":[],"categories":["Other Resources","Other Resource","Other Lists"],"sub_categories":["TeX Lists"],"readme":"\u003cp align=\"center\"\u003e\n  \u003ch1 align=\"center\"\u003e\n  Awesome Learning-based VO, VIO, and IO\n  \u003c/h1\u003e\n\u003c/p\u003e\n\nThis repository contains a curated list of resources addressing Learning-based visual odometry, visual-inertial odometry, and inertial odometry\n\nIf you find some ignored papers, **feel free to [*create pull requests*](https://github.com/KwanWaiPang/Awesome-Transformer-based-SLAM/blob/pdf/How-to-PR.md), or [*open issues*](https://github.com/KwanWaiPang/Awesome-Learning-based-VO-VIO/issues/new)**. \n\nContributions in any form to make this list more comprehensive are welcome.\n\nIf you find this repositorie is useful, a simple star should be the best affirmation. 😊\n\nFeel free to share this list with others!\n\n# Overview\n\n- [Learning-based VO](#Learning-based-VO)\n- [Learning-based VIO](#Learning-based-VIO)\n- [Learning-based IO](#Learning-based-IO)\n\n## Learning-based VO\n\n\u003c!-- |---|`arXiv`|---|---|---| --\u003e\n\u003c!-- [![Github stars](https://img.shields.io/github/stars/***.svg)]() --\u003e\n\n| Year | Venue | Paper Title | Repository | Note |\n|:----:|:-----:| ----------- |:----------:|:----:|\n|2024|`CVPR`|[Leap-vo: Long-term effective any point tracking for visual odometry](https://openaccess.thecvf.com/content/CVPR2024/papers/Chen_LEAP-VO_Long-term_Effective_Any_Point_Tracking_for_Visual_Odometry_CVPR_2024_paper.pdf)|[![Github stars](https://img.shields.io/github/stars/chiaki530/leapvo.svg)](https://github.com/chiaki530/leapvo)|[website](https://chiaki530.github.io/projects/leapvo/)|\n|2024|`RAL`|[Efficient Camera Exposure Control for Visual Odometry via Deep Reinforcement Learning](https://arxiv.org/pdf/2408.17005)|[![Github stars](https://img.shields.io/github/stars/ShuyangUni/drl_exposure_ctrl.svg)](https://github.com/ShuyangUni/drl_exposure_ctrl)|---| \n|2024|`ECCV`|[Reinforcement learning meets visual odometry](https://arxiv.org/pdf/2407.15626)|[![Github stars](https://img.shields.io/github/stars/uzh-rpg/rl_vo.svg)](https://github.com/uzh-rpg/rl_vo)|[Blog](https://kwanwaipang.github.io/RL-for-VO/)|\n|2024|`IROS`|[Deep Visual Odometry with Events and Frames](https://arxiv.org/pdf/2309.09947)|[![Github stars](https://img.shields.io/github/stars/uzh-rpg/rampvo.svg)](https://github.com/uzh-rpg/rampvo)|RAMP-VO| \n|2024|`3DV`|[Deep event visual odometry](https://arxiv.org/pdf/2312.09800)|[![Github stars](https://img.shields.io/github/stars/tum-vision/DEVO.svg)](https://github.com/tum-vision/DEVO)|---|\n|2024|`CVPR`|[Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization](https://arxiv.org/pdf/2404.15263)|[![Github stars](https://img.shields.io/github/stars/princeton-vl/MultiSlam_DiffPose.svg)](https://github.com/princeton-vl/MultiSlam_DiffPose)|Multi VO|\n|2024|`ECCV`|[Deep patch visual slam](https://arxiv.org/pdf/2408.01654)|[![Github stars](https://img.shields.io/github/stars/princeton-vl/DPVO.svg)](https://github.com/princeton-vl/DPVO)|---|\n|2024|`NIPS`|[Deep patch visual odometry](https://proceedings.neurips.cc/paper_files/paper/2023/file/7ac484b0f1a1719ad5be9aa8c8455fbb-Paper-Conference.pdf)|[![Github stars](https://img.shields.io/github/stars/princeton-vl/DPVO.svg)](https://github.com/princeton-vl/DPVO)|---|\n|2023|`ICRA`|[Dytanvo: Joint refinement of visual odometry and motion segmentation in dynamic environments](https://arxiv.org/pdf/2209.08430)|[![Github stars](https://img.shields.io/github/stars/castacks/DytanVO.svg)](https://github.com/castacks/DytanVO)|---|\n|2022|`Sensor`|[Raum-vo: Rotational adjusted unsupervised monocular visual odometry](https://www.mdpi.com/1424-8220/22/7/2651)|---|---|\n|2022|`Neurocomputing`|[DeepAVO: Efficient pose refining with feature distilling for deep Visual Odometry](https://arxiv.org/pdf/2105.09899)|---|---| \n|2021|`CoRL`|[Tartanvo: A generalizable learning-based vo](https://proceedings.mlr.press/v155/wang21h/wang21h.pdf)|[![Github stars](https://img.shields.io/github/stars/castacks/tartanvo.svg)](https://github.com/castacks/tartanvo)|---|\n|2021|`NIPS`|[DROID-SLAM: Deep Visual SLAM for Monocular,Stereo, and RGB-D Cameras](https://proceedings.neurips.cc/paper/2021/file/89fcd07f20b6785b92134bd6c1d0fa42-Paper.pdf)|[![Github stars](https://img.shields.io/github/stars/princeton-vl/DROID-SLAM.svg)](https://github.com/princeton-vl/DROID-SLAM)|---|\n|2021|`CVPR`|[Generalizing to the open world: Deep visual odometry with online adaptation](https://openaccess.thecvf.com/content/CVPR2021/papers/Li_Generalizing_to_the_Open_World_Deep_Visual_Odometry_With_Online_CVPR_2021_paper.pdf)|---|---|\n|2021|`arXiv`|[DF-VO: What should be learnt for visual odometry?](https://arxiv.org/pdf/2103.00933)|[![Github stars](https://img.shields.io/github/stars/Huangying-Zhan/DF-VO.svg)](https://github.com/Huangying-Zhan/DF-VO)|---|\n|2020|`ICRA`|[Visual odometry revisited: What should be learnt?](https://arxiv.org/pdf/1909.09803)|[![Github stars](https://img.shields.io/github/stars/Huangying-Zhan/DF-VO.svg)](https://github.com/Huangying-Zhan/DF-VO)|---|\n|2020|`CVPR`|[Towards better generalization: Joint depth-pose learning without posenet](https://openaccess.thecvf.com/content_CVPR_2020/papers/Zhao_Towards_Better_Generalization_Joint_Depth-Pose_Learning_Without_PoseNet_CVPR_2020_paper.pdf)|[![Github stars](https://img.shields.io/github/stars/B1ueber2y/TrianFlow.svg)](https://github.com/B1ueber2y/TrianFlow)|---|\n|2020|`CVPR`|[Diffposenet: Direct differentiable camera pose estimation](https://openaccess.thecvf.com/content/CVPR2022/papers/Parameshwara_DiffPoseNet_Direct_Differentiable_Camera_Pose_Estimation_CVPR_2022_paper.pdf)|---|---| \n|2020|`CVPR`|[D3vo: Deep depth, deep pose and deep uncertainty for monocular visual odometry](https://openaccess.thecvf.com/content_CVPR_2020/papers/Yang_D3VO_Deep_Depth_Deep_Pose_and_Deep_Uncertainty_for_Monocular_CVPR_2020_paper.pdf)|---|[website](https://cvg.cit.tum.de/research/vslam/d3vo)| \n|2021|`IJCV`|[Unsupervised scale-consistent depth learning from video](https://arxiv.org/pdf/2105.11610)|[![Github stars](https://img.shields.io/github/stars/JiawangBian/SC-SfMLearner-Release.svg)](https://github.com/JiawangBian/SC-SfMLearner-Release)\u003cbr\u003e[![Github stars](https://img.shields.io/github/stars/JiawangBian/sc_depth_pl.svg)](https://github.com/JiawangBian/sc_depth_pl)|---|\n|2019|`NIPS`|[Unsupervised scale-consistent depth and ego-motion learning from monocular video](https://proceedings.neurips.cc/paper/2019/file/6364d3f0f495b6ab9dcf8d3b5c6e0b01-Paper.pdf)|[![Github stars](https://img.shields.io/github/stars/JiawangBian/SC-SfMLearner-Release.svg)](https://github.com/JiawangBian/SC-SfMLearner-Release)\u003cbr\u003e[![Github stars](https://img.shields.io/github/stars/JiawangBian/sc_depth_pl.svg)](https://github.com/JiawangBian/sc_depth_pl)|---|\n|2019|`ICRA`|[Ganvo: Unsupervised deep monocular visual odometry and depth estimation with generative adversarial networks](https://arxiv.org/pdf/1809.05786)|---|---|\n|2019|`CVPR`|[Recurrent neural network for (un-) supervised learning of monocular video visual odometry and depth](https://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Recurrent_Neural_Network_for_Un-Supervised_Learning_of_Monocular_Video_Visual_CVPR_2019_paper.pdf)|-|-| \n|2019|`ICRA`|[Pose graph optimization for unsupervised monocular visual odometry](https://arxiv.org/pdf/1903.06315)|---|---|\n|2018|`CVPR`|[Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction](https://openaccess.thecvf.com/content_cvpr_2018/papers/Zhan_Unsupervised_Learning_of_CVPR_2018_paper.pdf)|[![Github stars](https://img.shields.io/github/stars/Huangying-Zhan/Depth-VO-Feat.svg)](https://github.com/Huangying-Zhan/Depth-VO-Feat)|---|\n|2018|`ICRA`|[Undeepvo: Monocular visual odometry through unsupervised deep learning](https://arxiv.org/pdf/1709.06841)|-|[website](https://senwang.gitlab.io/UnDeepVO/)|\n|2017|`ICRA`|[Deepvo: Towards end-to-end visual odometry with deep recurrent convolutional neural networks](https://arxiv.org/pdf/1709.08429)|-|[website](https://senwang.gitlab.io/DeepVO/)|\n|2017|`CVPR`|[Unsupervised learning of depth and ego-motion from video](https://openaccess.thecvf.com/content_cvpr_2017/papers/Zhou_Unsupervised_Learning_of_CVPR_2017_paper.pdf)|[![Github stars](https://img.shields.io/github/stars/tinghuiz/SfMLearner.svg)](https://github.com/tinghuiz/SfMLearner)|---|\n\n\n## Learning-based VIO\n\n\u003c!-- |---|`arXiv`|---|---|---| --\u003e\n\u003c!-- [![Github stars](https://img.shields.io/github/stars/***.svg)]() --\u003e\n\n| Year | Venue | Paper Title | Repository | Note |\n|:----:|:-----:| ----------- |:----------:|:----:|\n|2025|`Robotics and Autonomous Systems`|[CUAHN-VIO: Content-and-uncertainty-aware homography network for visual-inertial odometry](https://www.sciencedirect.com/science/article/pii/S0921889024002501)|[![Github stars](https://img.shields.io/github/stars/tudelft/CUAHN-VIO.svg)](https://github.com/tudelft/CUAHN-VIO)|---|\n|2025|`TRO`|[Airslam: An efficient and illumination-robust point-line visual slam system](https://arxiv.org/pdf/2408.03520)| [![Github stars](https://img.shields.io/github/stars/sair-lab/AirSLAM.svg)](https://github.com/sair-lab/AirSLAM)|---|\n|2024|`arXiv`|[SF-Loc: A Visual Mapping and Geo-Localization System based on Sparse Visual Structure Frames](https://arxiv.org/pdf/2412.01500)|[![Github stars](https://img.shields.io/github/stars/GREAT-WHU/SF-Loc.svg)](https://github.com/GREAT-WHU/SF-Loc)|[test](https://kwanwaipang.github.io/SF-Loc/)|\n|2024|`arXiv`|[DEIO: Deep Event Inertial Odometry](https://arxiv.org/pdf/2411.03928)|[![Github stars](https://img.shields.io/github/stars/arclab-hku/DEIO.svg)](https://github.com/arclab-hku/DEIO)|[website](https://kwanwaipang.github.io/DEIO/)|\n|2024|`CVPR`|[Adaptive vio: Deep visual-inertial odometry with online continual learning](https://openaccess.thecvf.com/content/CVPR2024/papers/Pan_Adaptive_VIO_Deep_Visual-Inertial_Odometry_with_Online_Continual_Learning_CVPR_2024_paper.pdf)|---|---|\n|2024|`RAL`|[DBA-Fusion: Tightly Integrating Deep Dense Visual Bundle Adjustment with Multiple Sensors for Large-Scale Localization and Mapping](https://arxiv.org/pdf/2403.13714)|[![Github stars](https://img.shields.io/github/stars/GREAT-WHU/DBA-Fusion.svg)](https://github.com/GREAT-WHU/DBA-Fusion)|---|\n|2024|`ICRA`|[DVI-SLAM: A dual visual inertial SLAM network](https://arxiv.org/pdf/2309.13814)|---|---|\n|2023|`ICRA`|[Bamf-slam: bundle adjusted multi-fisheye visual-inertial slam using recurrent field transforms](https://arxiv.org/pdf/2306.01173)|---|---|\n|2022|`ECCV`|[Efficient deep visual and inertial odometry with adaptive visual modality selection](https://arxiv.org/pdf/2205.06187)|[![Github stars](https://img.shields.io/github/stars/mingyuyng/Visual-Selective-VIO.svg)](https://github.com/mingyuyng/Visual-Selective-VIO)|---|\n|2022|`IEEE/ASME International Conference on Advanced Intelligent Mechatronics`|[A self-supervised, differentiable Kalman filter for uncertainty-aware visual-inertial odometry](https://arxiv.org/pdf/2203.07207)|---|---| \n|2022|`Neural Networks`|[SelfVIO: Self-supervised deep monocular Visual–Inertial Odometry and depth estimation](https://www.sciencedirect.com/science/article/pii/S0893608022000752)|---|---|\n|2021|`International Conference on International Joint Conferences on Artificial Intelligence`|[Unsupervised monocular visual-inertial odometry network](https://www.ijcai.org/proceedings/2020/0325.pdf)|[![Github stars](https://img.shields.io/github/stars/Ironbrotherstyle/UnVIO.svg)](https://github.com/Ironbrotherstyle/UnVIO)|---|\n|2021|`IEEE International Conference on Acoustics, Speech and Signal Processing `|[Atvio: Attention guided visual-inertial odometry](https://github.com/KwanWaiPang/Awesome-Learning-based-VO-VIO/blob/pdf/file/ATVIO_Attention_Guided_Visual-Inertial_Odometry.pdf)|---|---|\n|2019|`TPAMI`|[Unsupervised deep visual-inertial odometry with online error correction for RGB-D imagery](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8691513)|---|---|\n|2019|`CVPR`|[Selective sensor fusion for neural visual-inertial odometry](https://openaccess.thecvf.com/content_CVPR_2019/papers/Chen_Selective_Sensor_Fusion_for_Neural_Visual-Inertial_Odometry_CVPR_2019_paper.pdf)|---|---|\n|2019|`IROS`|[Deepvio: Self-supervised deep learning of monocular visual inertial odometry using 3d geometric constraints](https://arxiv.org/pdf/1906.11435)|---|---| \n|2017|`AAAI`|[Vinet: Visual-inertial odometry as a sequence-to-sequence learning problem](https://arxiv.org/pdf/1701.08376)|[![Github stars](https://img.shields.io/github/stars/HTLife/VINet.svg)](https://github.com/HTLife/VINet)|non-official implementation|\n\n\n## Learning-based IO\n\n\u003c!-- |---|`arXiv`|---|---|---| --\u003e\n\u003c!-- [![Github stars](https://img.shields.io/github/stars/***.svg)]() --\u003e\n| Year | Venue | Paper Title | Repository | Note |\n|:----:|:-----:| ----------- |:----------:|:----:|\n|2025|`arXiv`|[AirIO: Learning Inertial Odometry with Enhanced IMU Feature Observability](https://arxiv.org/pdf/2501.15659)|[![Github stars](https://img.shields.io/github/stars/Air-IO/Air-IO.svg)](https://github.com/Air-IO/Air-IO)|[website](https://air-io.github.io/)\u003cbr\u003e[Test](https://kwanwaipang.github.io/AirIO/)|\n|2024|`TIV`|[Deep learning for inertial positioning: A survey](https://arxiv.org/pdf/2303.03757)|---|---|\n|2023|`arXiv`|[End-to-end deep learning framework for real-time inertial attitude estimation using 6dof imu](https://www.researchgate.net/profile/Arman-Asgharpoor-Golroudbari/publication/368469434_END-TO-END_DEEP_LEARNING_FRAMEWORK_FOR_REAL-TIME_INERTIAL_ATTITUDE_ESTIMATION_USING_6DOF_IMU/links/63ea42cebd7860764364396a/End-to-End-Deep-Learning-Framework-for-Real-Time-Inertial-Attitude-Estimation-using-6DoF-IMU.pdf)|---|---|\n|2023|`arXiv`|[AirIMU: Learning uncertainty propagation for inertial odometry](https://arxiv.org/pdf/2310.04874)|[![Github stars](https://img.shields.io/github/stars/haleqiu/AirIMU.svg)](https://github.com/haleqiu/AirIMU)|[website](https://airimu.github.io/)\u003cbr\u003e[Test](https://kwanwaipang.github.io/AirIMU/)|\n|2023|`RAL`|[Learned inertial odometry for autonomous drone racing](https://arxiv.org/pdf/2210.15287)|[![Github stars](https://img.shields.io/github/stars/uzh-rpg/learned_inertial_model_odometry.svg)](https://github.com/uzh-rpg/learned_inertial_model_odometry)|---|\n|2022|`ICRA`|[Improved state propagation through AI-based pre-processing and down-sampling of high-speed inertial data](https://www.aau.at/wp-content/uploads/2022/03/imu_preprocessing.pdf)|---|---|\n|2022|`RAL`|[Deep IMU Bias Inference for Robust Visual-Inertial Odometry with Factor Graphs](https://arxiv.org/pdf/2211.04517)|---|---|\n|2021|`ICRA`|[IMU Data Processing For Inertial Aided Navigation:A Recurrent Neural Network Based Approach](https://arxiv.org/pdf/2103.14286)|---|---|\n\n\n\n## Other Related Resource\n* [Awesome-Transformer-based-SLAM](https://github.com/KwanWaiPang/Awesome-Transformer-based-SLAM)\n* [Blog for Learning-based VO and VIO](https://kwanwaipang.github.io/Learning-based-VO-VIO/)\n* [Blog for Deep IMU-Bias Inference](https://kwanwaipang.github.io/Deep-IMU-Bias/)\n* Some related papers for learning-based VO,VIO, such as dataset, depth estimation, etc.\n\n\u003c!-- |---|`arXiv`|---|---|---| --\u003e\n\u003c!-- [![Github stars](https://img.shields.io/github/stars/***.svg)]() --\u003e\n| Year | Venue | Paper Title | Repository | Note |\n|:----:|:-----:| ----------- |:----------:|:----:|\n|2024|`TPAMI`|[Metric3d v2: A versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation](https://arxiv.org/pdf/2404.15506)|[![Github stars](https://img.shields.io/github/stars/YvanYin/Metric3D.svg)](https://github.com/YvanYin/Metric3D)|[website](https://jugghm.github.io/Metric3Dv2/)\u003cbr\u003edepth estimation|\n|2022|`NIPS`|[Theseus: A library for differentiable nonlinear optimization](https://proceedings.neurips.cc/paper_files/paper/2022/file/185969291540b3cd86e70c51e8af5d08-Paper-Conference.pdf)|[![Github stars](https://img.shields.io/github/stars/facebookresearch/theseus.svg)](https://github.com/facebookresearch/theseus)|[website](https://sites.google.com/view/theseus-ai/)|\n|2020|`CVPR`|[Superglue: Learning feature matching with graph neural networks](https://openaccess.thecvf.com/content_CVPR_2020/papers/Sarlin_SuperGlue_Learning_Feature_Matching_With_Graph_Neural_Networks_CVPR_2020_paper.pdf)|[![Github stars](https://img.shields.io/github/stars/magicleap/SuperGluePretrainedNetwork.svg)](https://github.com/magicleap/SuperGluePretrainedNetwork)|---|\n|2020|`IROS`|[Tartanair: A dataset to push the limits of visual slam](https://arxiv.org/pdf/2003.14338)|[![Github stars](https://img.shields.io/github/stars/castacks/tartanair_tools.svg)](https://github.com/castacks/tartanair_tools)|[website](https://theairlab.org/tartanair-dataset/)|\n|2020|`ECCV`|[Raft: Recurrent all-pairs field transforms for optical flow](https://arxiv.org/pdf/2003.12039)|[![Github stars](https://img.shields.io/github/stars/princeton-vl/RAFT.svg)](https://github.com/princeton-vl/RAFT)|---|\n|2019|`CVPR`|[Projective manifold gradient layer for deep rotation regression](https://openaccess.thecvf.com/content/CVPR2022/papers/Chen_Projective_Manifold_Gradient_Layer_for_Deep_Rotation_Regression_CVPR_2022_paper.pdf)|[![Github stars](https://img.shields.io/github/stars/JYChen18/RPMG.svg)](https://github.com/JYChen18/RPMG)|Better learn rotations|\n|2018|`ECCV`|[Mvsnet: Depth inference for unstructured multi-view stereo](https://openaccess.thecvf.com/content_ECCV_2018/papers/Yao_Yao_MVSNet_Depth_Inference_ECCV_2018_paper.pdf)|---|---|\n|2018|`CVPR`|[Superpoint: Self-supervised interest point detection and description](https://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w9/DeTone_SuperPoint_Self-Supervised_Interest_CVPR_2018_paper.pdf)|[![Github stars](https://img.shields.io/github/stars/rpautrat/SuperPoint.svg)](https://github.com/rpautrat/SuperPoint)|[pytorch version](https://github.com/eric-yyjau/pytorch-superpoint)\u003cbr\u003e[event superpoint](https://github.com/mingyip/pytorch-superpoint)|\n|2015|`ICCV`|[Flownet: Learning optical flow with convolutional networks](https://openaccess.thecvf.com/content_iccv_2015/papers/Dosovitskiy_FlowNet_Learning_Optical_ICCV_2015_paper.pdf)|---|---|\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FKwanWaiPang%2FAwesome-Learning-based-VO-VIO","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FKwanWaiPang%2FAwesome-Learning-based-VO-VIO","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FKwanWaiPang%2FAwesome-Learning-based-VO-VIO/lists"}