关于我
Xiao Liu (刘骁)
E-mail: liuxiao (at) foxmail.com
I joined the PICO department at ByteDance in December 2021 as the head of the Mixed Reality (MR) algorithms team. Prior to that, I spent four years (from October 2017 to December 2021) at Megvii (Face++) Research, serving as the Director responsible for 3D vision algorithm research. Between December 2010 and October 2017, I worked at Tencent Technology (Beijing) Co., Ltd., contributing to both the WeChat and Tencent Research departments as a pattern recognition algorithm researcher.
I earned my Master's degree in Computer Science from BeiHang University in January 2011, following my Bachelor's degree in Science from the same institution in July 2007.
My research interests span 3D vision (encompassing 3D reconstruction, 3D AIGC, and 3D scene understanding), computer vision, SLAM (Simultaneous Localization and Mapping), robotics, among others.
Interests
Computer Vision, 3D Vision, SLAM, AR/VR, Robotics
Professional Experience
时间 | 公司 | 部门 | 职位 |
2021.12-至今 | 字节跳动 | PICO | MR 团队负责人 |
2017.10-2021.12 | 旷视科技有限公司 | 研究院 | 3D 部门总监 |
2013.10-2017.10 | 腾讯科技(北京)有限公司 | 微信产品部 | 高级研究员 |
2010.12-2013.10 | 腾讯科技(北京)有限公司 | 研究院 | 高级研究员 |
2010.06-2010.11 | 佳能信息(北京)有限公司 | 研究院 | OCR 研究员(实习) |
2009.09-2010.04 | 联想研究院 | 移动互联网技术部 | 研究员(实习) |
Education
时间 | 学校 | 院系 | 学历 |
2008.9-2011.1 | 北京航空航天大学 | 计算机科学与技术 | 硕士研究生 |
2003.9-2007.7 | 北京航空航天大学 | 应用物理(应用电子技术) | 本科 |
Research
Challenge Winnings
年份 | 比赛 | 链接 |
2024 | CVPR 2024 3D Open-Vocabulary Scene Understanding (OpenSUN3D) Challenge Zhishan Zhou, Yunke Cai, Chunjie Wang, Xiaosheng Yan, Bingwen Wang, Xiao Liu PICO-MR Team 1st place in 3D Functionality Grounding 2nd place in 3D Object Instance Search | Workshop | Challenge Track 1 Track 2 | More >> |
2024 | CVPR 2024 Monocular Depth Estimation Challenge GuangYuan Zhou, ZhengXin Li, Qiang Rao, YiPing Bao, Xiao Liu 1st place | Results | Workshop | Challenge | More >> |
2023 | ICCV 2023 3D Open-Vocabulary Scene Understanding (OpenSUN3D) Challenge Hongbo Tian, Chunjie Wang, Xiaosheng Yan, Bingwen Wang, Xuanyang Zhang, Xiao Liu 1st place | Results | Workshop | Challenge | More >> |
2021 | ICCV 2021 Long-Term Visual Localization under Changing Conditions Challenge Shuxue Peng, Zihang He, Haotian Zhang, Ran Yan, Chuting Wang, Qingtian Zhu, Yikang Ding, Liangtao Zheng and Xiao Liu 1st place in Outdoor visual localization track 1st place in Indoor visual localization track | Website | Workshop | Recording | More >> |
2021 | ICCV 2021 Map-Based Localization for Autonomous Driving Challenge Megvii 3D Team 1st place | Website | Workshop | Recording | More >> |
2021 | CVPR 2021 Image Matching Challenge Xiaopeng Bi, Yu Chen, Xinyang Liu, Dehao Zhang, Ran Yan, Zheng Chai, Haotian Zhang, and Xiao Liu 1st place in Unlimited keypoints category 1st place in SimLocMatch competition 2nd place in Restricted keypoints category | Website | Recording 1. IMC 2021 Challenge | Report 2. SimLocMatch Challenge | Report |
2021 | IROS 2021 THE HILTI SLAM Challenge Xiaojia Xie, Xizhen Xiao, Xuefeng Shen, Wei Zuo, and Xiao Liu 1st place | Website | Workshop | Report | More >> |
2020 | CVPR 2020 SLAM Challenge Haotian Zhang, Zheng Chai, and Xiao Liu 1st place in Mono Track competition 1st place in Stereo Track competition | Website | Recording | More >> |
Recent Publications
论文/作者 | 会议/期刊 | 下载 |
Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning Wenqi Dong, Bangbang Yang, Lin Ma, Xiao Liu, Liyuan Cui, Hujun Bao, Yuewen Ma, Zhaopeng Cui | SIGGRAPH 2024 | Paper |
Multi-modal Relation Distillation for Unified 3D Representation Learning Huiqun Wang, Yiping Bao, Panwang Pan, Zeming Li, Xiao Liu, Ruijie Yang, Di Huang | ECCV 2024 | Paper |
DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagation Bangbang Yang, Wenqi Dong, Lin Ma, Wenbo Hu, Xiao Liu, Zhaopeng Cui, Yuewen Ma | IEEE VR 2024 | Paper |
Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields Wenbo Hu, Yuling Wang, Lin Ma, Bangbang Yang, Lin Gao, Xiao Liu, Yuewen Ma | ICCV 2023 Oral Bestpaper Finalist 17/8260 | Paper |
MegBA: A High-Performance and Distributed Library for Large-Scale Bundle Adjustment Jie Ren, Wenteng Liang, Ran Yan, Luo Mai, Shiwen Liu, Xiao Liu | ECCV 2022 | Paper |
TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers Yikang Ding, Wentao Yuan, Qingtian Zhu, Haotian Zhang, Xiangyue Liu, Yuanjiang Wang, Xiao Liu | CVPR 2022 | Paper |
ELSD: Efficient Line Segment Detector and Descriptor Haotian Zhang, Yicheng Luo, Fangbo Qin, Yijia He, Xiao Liu | ICCV 2021 | Paper |
M^3VSNet: Unsupervised Multi-metric Multi-view Stereo Network Baichuan Huang, Hongwei Yi, Can Huang, Yijia He, Jingbin Liu, Xiao Liu | ICIP 2021 | Paper |
Structure Reconstruction Using Ray-Point-Ray Features: Representation, Triangulation and Camera Pose Estimation Yijia He, Xiangyue Liu, Xiao Liu, Ji Zhao | ICRA 2021 | |
Monocular Visual SLAM with Points and Lines for Ground Robots in Particular Scenes: Parameterization for Lines on Ground Meixiang Quan, Songhao Piao, Yijia He, Xiao Liu & Muhammad Zuhair Qadir | J Intell Robot Syst 101, 72 (2021) | |
TP-LSD: Tri-Points Based Line Segment Detector Siyu Huang, Fangbo Qin, Pengfei Xiong, Ning Ding, Yijia He, Xiao Liu | ECCV 2020 | Paper |
Leveraging Planar Regularities for Point Line Visual-Inertial Odometry Xin Li, Yijia He, Jinlong Lin, Xiao Liu | IROS 2020 | Paper |
MLIFeat: Multi-level information fusion based deep local features Yuyang Zhang,Jinge Wang,Shibiao Xu,Xiao Liu,Xiaopeng Zhang | ACCV 2020 | Paper |
Coarse-To-Fine Visual Localization Using Semantic Compact Map Ziwei Liao, Jieqi Shi , Xianyu Qi, Xiaoyu Zhang, Wei Wang, Yijia He, Xiao Liu , Ran Wei | ICCR 2020 | Paper |
Talks
Talk | Talk | 地址 |
将门公开课 2020 | 三维视觉与机器人 | 链接 |
SIGGRAPH Asia 2016 | QAR Open Platform | 链接 |
【请教】有关你写的MXNet的image-classification-predict.cc的疑问
liuxiao你好,
我看到你贡献给MXNet的image-classification-predict.cc代码做predict。
https://github.com/dmlc/mxnet/blob/master/example/cpp/image-classification/image-classification-predict.cc
有个疑问请教一下。
在GetMeanFile中你是直接设置mean=117,你的注释里也写着:
// Better to be read from a mean.nb file
我现在有图像均值的二进制文件mean.bin,想直接整张图片做矩阵减,
还请问该如何读文件 以及做后续的norm操作呢?
直接用你的数值在我的数据集上预测结果不佳,
而且实验发现修改该值对最终的top-1预测结果影响很大
希望能够获得你的帮助,非常感谢!
hi,我昨晚抽空改了下提交了个 patch,试了几张图应该和以前没有变化。你看能不能解决你说的问题:
https://github.com/dmlc/mxnet/pull/1507
Xiao Liu
Hi 技术刘, skylook,
你们好! 请问能帮忙看看以下的问题吗?
https://github.com/dmlc/mxnet/issues/2709
谢谢!
WeiSheng
您好我有个关于image-classification-predict.cc的疑问
我想在windows环境下运行这个demo但是在windows下编译的dll跟lib使用时会报error LNK2001: 无法解析的外部符号 __imp__MXPredFree D:\poi\testcv_mxnetnet\testcv\Source.obj
这样错误,用官方预编译的版本也会这样,怎么解决啊?
抱歉,没有用 windows 编译过 mxnet。
liuxiao.net
Not needed.
你好,这篇文章里,你对比了vi-orb-slam和orb slam的定位精度,但是我理解orb slam应该是得不到尺度信息的,而vi-orb-slam是有尺度的,你给出的rmse应该是实际的物理值,那orb slam的rmse值是怎么得到的呢? 另外,rmse是指的关键帧的计算位置和ground truth的位置的误差吗? 谢谢
liuxiao 你好,你的这篇文章里,你对比了vi-orb-slam和orb slam的定位精度,但是我理解orb slam应该是得不到尺度信息的,而vi-orb-slam是有尺度的,你给出的rmse应该是实际的物理值,那orb slam的rmse值是怎么得到的呢? 另外,rmse是指的关键帧的计算位置和ground truth的位置的误差吗? 谢谢
orb slam双目可以估计绝对尺度,单目是用拟合算法拟合出一个与真值最接近的scale作为绝对尺度再进行估计。这些方法在前面的博文中evo工具均有提供。rmse是关键帧的位置和GT的误差
1. orb-slam2 保存的相机轨迹和groundtruth有很大的区别,完全不吻合。是不是坐标系的问题啊?orb-slam2没做坐标变换?
2. orb-slam2 有木有加入IMU信息的版本啊?
1、如果运行正确没有问题,请参见:https://www.liuxiao.org/2017/11/%E4%BD%BF%E7%94%A8-evo-%E5%B7%A5%E5%85%B7%E8%AF%84%E6%B5%8B-vi-orb-slam2-%E5%9C%A8-euroc-%E4%B8%8A%E7%9A%84%E7%BB%93%E6%9E%9C/
2、加入IMU信息的没有官方版本只有王京等一些人个人的一些实验代码。
hello,关于mxnet里的example。我想在自己的系统里面使用mxnet的结果,做相近的sementation的工作,只需要将lib文件里编译好的库文件复制到本地文件就可以了吗?那cmakelist里面需要怎么链接呢?看您提供的makefile不是很明白。
liuxiao.net出售
有没有C风格的调用mxnet的例子, 想用rust 绑定一下
(嘤嘤怪出没)
最近许久没有再研究mxnet了
单目是用拟合算法拟合出一个与真值最接近的scale作为绝对尺度再进行估计。大佬,这句话我没有太理解,有没有参考的资料,我学习下。最近有点纠结这个单目的scale。谢谢
Hi 刘先生
我是无人驾驶领域猎头刘敏,关注到您在腾讯的工作,我正在帮我北上深杭苏的无人驾驶客户寻找SLAM这块的职位,期望能与您交换个电话号码做进一步沟通,我的电话是15959217633(微信同号),期待您的消息。
刘敏
哇,现在猎头同志这么专业都上博客了
666 tql
我也是,哈哈
你好,巧合下看到你的博客,想了解一下在deep vslam这块的一些问题。UnSuperPoint在我看到的几个复现中都表示学习不出特征的位置,结果是一个均匀分布的检测结果。所以想问一下博主关于UnSuperPoint里面,点对选取和score map的选择。看了解读的文章还是不太明确,像GCN的思路就是直接用其它的关键点检测方法,得到原图的特征点,然后进行投影得到变换图的数据。这个思路应该是好理解的。但是UnSuperPoint或者SuperPoint似乎没有用第三方的特征点检测方法,那如何确定关键点的位置和描述子呢。
SuperPoint 是通过在仿真数据集上训练一个可以预测几何角点的 MagicPoint 再用它在真实数据集做 Homography Adaptation 获得真值,本质上是一个弱标记的方式。具体在他的论文中讲得还是很清楚的。
UnSuperPoint 是完全的无监督方式,具体参见 Figure 3,它构造的 Loss 本质上是学习在各种不同 Homography 变化下依然能够匹配的点,这种方式在其他文章中也出现过。对于后者由于没有实现过,是否真的可行以及是否实际上需要预训练参数,还是存疑的。
搞技术的好牛逼啊,真是佩服,北航师弟膜拜