直播预告 | 华南理工实验室专场一

4月28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一！

杨明玥：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。研究兴趣包括三维计算机视觉与深度学习。

摘要：

Many learning-based approaches have difficulty scaling to unseen data, as the generality of its learned prior is limited to the scale and variations of the training samples. This holds particularly true with 3D learning tasks, given the sparsity of 3D datasets available. We introduce a new learning framework for 3D modeling and reconstruction that greatly improves the generalization ability of a deep generator. Our approach strives to connect the good ends of both learning-based and optimization-based methods. In particular, unlike the common practice that fixes the pre-trained priors at test time, we propose to further optimize the learned prior and latent code according to the input physical measurements after the training. We show that the proposed strategy effectively breaks the barriers constrained by the pre-trained priors and could lead to high-quality adaptation to unseen data. We realize our framework using the implicit surface representation and validate the efficacy of our approach in a variety of challenging tasks that take highly sparse or collapsed observations as input. Experimental results show that our approach compares favorably with the state-of-the-art methods in terms of both generality and accuracy.

论文标题：

Deep Optimized Priors for 3D Shape Modeling and Reconstruction

论文链接：

https://www.aminer.cn/pub/5fd8a0e191e0119b22c1f2ca/deep-optimized-priors-for-d-shape-modeling-and-reconstruction

邓圣衡：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。研究兴趣包括计算机视觉与深度学习。

摘要：

The ability to understand the ways to interact with objects from visual cues, a.k.a. visual affordance, is essential to vision-guided robotic research. This involves categorizing, segmenting and reasoning of visual affordance. Relevant studies in 2D and 2.5D image domains have been made previously, however, a truly functional understanding of object affordance requires learning and prediction in the 3D physical domain, which is still absent in the community. In this work, we present a 3D AffordanceNet dataset, a benchmark of 23k shapes from 23 semantic object categories, annotated with 18 visual affordance categories. Based on this dataset, we provide three benchmarking tasks for evaluating visual affordance understanding, including full-shape, partial-view and rotation-invariant affordance estimations. Three state-of-the-art point cloud deep learning networks are evaluated on all tasks. In addition we also investigate a semi-supervised learning setup to explore the possibility to benefit from unlabeled data. Comprehensive results on our contributed dataset show the promise of visual affordance understanding as a valuable yet challenging benchmark. 

论文标题：

3D AffordanceNet: A Benchmark for Visual Object Affordance

论文链接：

https://www.aminer.cn/pub/606460bc91e011538305d109/d-affordancenet-a-benchmark-for-visual-object-affordance-understanding

温宇馨：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博士四年级，导师为贾奎教授。研究兴趣包括计算机视觉与机器学习。已在相关领域的国际顶级会议期刊如ICML, CVPR, TPAMI等发表多篇论文。

摘要：

Machine learning models have been shown to be vulnerable to adversarial examples. While most of the existing methods for adversarial attack and defense work on the 2D image domain, a few recent attempts have been made to extend them to 3D point cloud data. However, adversarial results obtained by these methods typically contain point outliers, which are both noticeable and easy to defend against using the simple techniques of outlier removal. Motivated by the different mechanisms by which humans perceive 2D images and 3D shapes, in this paper we propose the new design of geometry-aware objectives, whose solutions favor (the discrete versions of) the desired surface properties of smoothness and fairness. To generate adversarial point clouds, we use a targeted attack misclassification loss that supports continuous pursuit of increasingly malicious signals. Regularizing the targeted attack loss with our proposed geometry-aware objectives results in our proposed method, Geometry-Aware Adversarial Attack (GeoA3). The results of GeoA3 tend to be more harmful, arguably harder to defend against, and of the key adversarial characterization of being imperceptible to humans. While the main focus of this paper is to learn to generate adversarial point clouds, we also present a simple but effective algorithm termed Geo+A3-IterNormPro, with Iterative Normal Projection (IterNorPro) that solves a new objective function Geo+A3, towards surface-level adversarial attacks via generation of adversarial point clouds. We quantitatively evaluate our methods on both synthetic and physical objects in terms of attack success rate and geometric regularity. For a qualitative evaluation, we conduct subjective studies by collecting human preferences from Amazon Mechanical Turk. Comparative results in comprehensive experiments confirm the advantages of our proposed methods. 

论文标题：

Geometry-Aware Generation of Adversarial Point Clouds

论文链接：

https://www.aminer.cn/pub/5fdb2d62d4150a363c996dfa/geometry-aware-generation-of-adversarial-point-clouds