点击蓝字
关注我们
AI TIME欢迎每一位AI爱好者的加入!
4月2日晚7:30-9:00
AI TIME特别邀请了两位优秀的讲者跟大家共同开启浙大CAD&CG实验室专场二!
哔哩哔哩直播通道
扫码关注AITIME哔哩哔哩官方账号
观看直播
链接:https://live.bilibili.com/21813994
★ 邀请嘉宾 ★
黄昭阳:现为香港中文大学MMLab一年级博士生(导师:李鸿升),2019年硕士毕业于浙江大学CAD&CG国家重点实验室(导师:章国锋)。相关研究成果发表在顶级会议与期刊ICCV, CVPR, TVCG上。
报告题目:
基于像素投票与图像分割的视觉定位
摘要:
Visual localization is of great importance in robotics and computer vision. Recently, scene coordinate regression based methods have shown good performance in visual localization in small static scenes. However, it still estimates camera poses from many inferior scene coordinates. To address this problem, we propose a novel visual localization framework that establishes 2D-to-3D correspondences between the query image and the 3D map with a series of learnable scene-specific landmarks. In the landmark generation stage, the 3D surfaces of the target scene are over-segmented into mosaic patches whose centers are regarded as the scene-specific landmarks. To robustly and accurately recover the scene-specific landmarks, we propose the Voting with Segmentation Network (VS-Net) to segment the pixels into different landmark patches with a segmentation branch and estimate the landmark locations within each patch with a landmark location voting branch. Since the number of landmarks in a scene may reach up to 5000, training a segmentation network with such a large number of classes is both computation and memory costly for the commonly used cross-entropy loss. We propose a novel prototype-based triplet loss with hard negative mining, which is able to train semantic segmentation networks with a large number of labels efficiently. Our proposed VS-Net is extensively tested on multiple public benchmarks and can outperform state-of-the-art visual localization methods.
论文标题:
VS-Net: Voting with Segmentation for Visual Localization
论文链接:
http://www.cad.zju.edu.cn/home/xzhou/publication/cvpr2021vs/
谢一鸣:浙江大学CAD&CG国家重点实验室科研助理(导师:周晓巍)。主要研究方向为三维场景重建与三维物体检测。相关研究成果在CVPR等学术会议上发表。本科毕业于浙江大学。
报告题目:
基于单目视频的三维场景实时重建
摘要:
We present a novel framework named NeuralRecon for real-time 3D scene reconstruction from a monocular video. Unlike previous methods that estimate single-view depth maps separately on each key-frame and fuse them later, we propose to directly reconstruct local surfaces represented as sparse TSDF volumes for each video fragment sequentially by a neural network. A learning-based TSDF fusion module based on gated recurrent units is used to guide the network to fuse features from previous fragments. This design allows the network to capture local smoothness prior and global shape prior of 3D surfaces when sequentially reconstructing the surfaces, resulting in accurate, coherent, and real-time surface reconstruction. The experiments on ScanNet and 7-Scenes datasets show that our system outperforms state-of-the-art methods in terms of both accuracy and speed. To our best knowledge, this is the first learning-based system that is able to reconstruct dense coherent 3D geometry in real-time.
论文标题:
NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
论文链接:
https://zju3dv.github.io/neuralrecon‘
直播结束后我们会邀请讲者在微信群中与大家答疑交流,请添加“AI TIME小助手(微信号:AITIME_HY)”,回复“PhD”,将拉您进“PhD交流群”!
AI TIME微信小助手
主 办:AI TIME 、AMiner
合作伙伴:智谱·AI、中国工程院知领直播、学堂在线、学术头条、biendata、数据派、 Ever链动、机器学习算法与自然语言处理
AMiner是学术搜索和社会网络挖掘研究的重要数据和实验平台,由清华大学计算机系研发,拥有我国完全自主知识产权。平台包含了超过2.3亿学术论文/专利和1.36亿学者的科技图谱,提供学者评价、专家发现、智能指派、学术地图等科技情报专业化服务。系统2006年上线,吸引了全球220个国家/地区1000多万独立IP访问,数据下载量230万次,年度访问量超过1100万。
AMiner平台:https://www.aminer.cn
AI TIME欢迎AI领域学者投稿,期待大家剖析学科历史发展和前沿技术。针对热门话题,我们将邀请专家一起论道。同时,我们也长期招募优质的撰稿人,顶级的平台需要顶级的你,
请将简历等信息发至yun.he@aminer.cn!
微信联系:AITIME_HY
AI TIME是清华大学计算机系一群关注人工智能发展,并有思想情怀的青年学者们创办的圈子,旨在发扬科学思辨精神,邀请各界人士对人工智能理论、算法、场景、应用的本质问题进行探索,加强思想碰撞,打造一个知识分享的聚集地。
更多资讯请扫码关注
我知道你在看哟
点击 阅读原文 写下你的问题