直播预告 | 华南理工实验室专场二

点击蓝字

关注我们

AI TIME欢迎每一位AI爱好者的加入！

4月30日晚7:30-9:00

AI TIME特别邀请了三位优秀的讲者跟大家共同开启华南理工-几何感知与智能实验室专场二！

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 ★

唐佳鹏：本科毕业于华南理工大学，目前在华南理工大学几何感知与智能实验室就读硕士三年级，导师为贾奎教授。研究兴趣包括三维计算机视觉和深度学习。已在相关领域的国际顶级会议如CVPR， ICCV等发表多篇论文。

报告题目：

基于隐式场的实时动态人体重建

摘要：

This paper focuses on the task of 4D shape reconstruction from a sequence of point clouds. Despite the recent success achieved by extending deep implicit representations into 4D space, it is still a great challenge in two respects, i.e. how to design a flexible framework for learning robust spatio-temporal shape representations from 4D point clouds, and develop an efficient mechanism for capturing shape dynamics. In this work, we present a novel pipeline to learn a temporal evolution of the 3D human shape through spatially continuous transformation functions among cross-frame occupancy fields. The key idea is to parallelly establish the dense correspondence between predicted occupancy fields at different time steps via explicitly learning continuous displacement vector fields from robust spatio-temporal shape representations. Extensive comparisons against previous state-of-the-arts show the superior accuracy of our approach for 4D human reconstruction in the problems of 4D shape auto-encoding and completion, and a much faster network inference with about 8 times speedup demonstrates the significant efficiency of our approach.

论文标题：

Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction

论文链接：

https://arxiv.org/pdf/2103.16341.pdf

赵文彬：本科毕业于华南理工大学，目前在华南理工大学几何感知与智能实验室就读硕士一年级，导师为贾奎教授/陈轲副教授。研究兴趣包括三维计算机视觉与深度学习。

报告题目：

无符号和自相似的三维点云隐式表面建模与重建

摘要：

Shape modeling and reconstruction from raw point clouds of objects stand as a fundamental challenge in vision and graphics research. Classical methods consider analytic shape priors; however, their performance is degraded when the scanned points deviate from the ideal conditions of cleanness and completeness. Important progress has been recently made by data-driven approaches, which learn global and/or local models of implicit surface representations from auxiliary sets of training shapes. Motivated from a universal phenomenon that self-similar shape patterns of local surface patches repeat across the entire surface of an object, we aim to push forward the data-driven strategies and propose to learn a local implicit surface network for a shared, adaptive modeling of the entire surface for a direct surface reconstruction from raw point cloud; we also enhance the leveraging of surface self-similarities by improving correlations among the optimized latent codes of individual surface patches. Given that orientations of raw points could be unavailable or noisy, we extend signagnostic learning into our local implicit model, which enables our recovery of signed implicit fields of local surfaces from the unsigned inputs. We term our framework as Sign-Agnostic Implicit Learning of Surface Self-Similarities (SAIL-S3). With a global post-optimization of local sign flipping, SAIL-S3 is able to directly model raw, un-oriented point clouds and reconstruct high-quality object surfaces. Experiments show its superiority over existing methods.

论文标题：

Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point CloudsUnderstanding

论文链接：

https://arxiv.org/abs/2012.07498

邓彬：硕士毕业于深圳大学计算机与软件学院，目前在华南理工大学几何感知与智能实验室就读博士一年级，导师为贾奎教授。研究兴趣包括高光谱遥感图像处理，模式识别，机器学习（迁移学习）等，在其相关领域顶级期刊发表论文多篇。

报告题目：

非监督多类域适应：理论，算法和实践

摘要：

In this paper, we study the formalism of unsupervised multi-class domain adaptation (multi-class UDA), which underlies a few recent algorithms whose learning objectives are only motivated empirically. Multi-Class Scoring Disagreement (MCSD) divergence is presented by aggregating the absolute margin violations in multi-class classification, and this proposed MCSD is able to fully characterize the relations between any pair of multi-class scoring hypotheses. By using MCSD as a measure of domain distance, we develop a new domain adaptation bound for multi-class UDA; its data-dependent, probably approximately correct bound is also developed that naturally suggests adversarial learning objectives to align conditional feature distributions across source and target domains. Consequently, an algorithmic framework of Multi-class Domain-adversarial learning Networks (McDalNets) is developed, and its different instantiations via surrogate learning objectives either coincide with or resemble a few recently popular methods, thus (partially) underscoring their practical effectiveness. Based on our identical theory for multi-class UDA, we also introduce a new algorithm of Domain-Symmetric Networks (SymmNets), which is featured by a novel adversarial strategy of domain confusion and discrimination. SymmNets affords simple extensions that work equally well under the problem settings of either closed set, partial, or open set UDA. We conduct careful empirical studies to compare different algorithms of McDalNets and our newly introduced SymmNets. Experiments verify our theoretical analysis and show the efficacy of our proposed SymmNets. 

论文标题：

Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice

论文链接：

https://arxiv.org/abs/2002.08681

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“phd2”，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

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