no code implementations • 21 Nov 2023 • Bo Sun, QiXing Huang, Xiangru Huang
In the experiments, our method significantly outperform existing approaches in 3D semantic segmentation on several public benchmarks, such as Waymo Open Dataset, SemanticKITTI and ScanNetV2.
1 code implementation • 20 Apr 2023 • Haitao Yang, Xiangru Huang, Bo Sun, Chandrajit Bajaj, QiXing Huang
GenCorres addresses this issue by learning an implicit generator from the input shapes, which provides intermediate shapes between two arbitrary shapes.
1 code implementation • 4 Apr 2023 • Haitao Yang, Zaiwei Zhang, Xiangru Huang, Min Bai, Chen Song, Bo Sun, Li Erran Li, QiXing Huang
Bird's-Eye View (BEV) features are popular intermediate scene representations shared by the 3D backbone and the detector head in LiDAR-based object detectors.
1 code implementation • ICCV 2021 • QiXing Huang, Xiangru Huang, Bo Sun, Zaiwei Zhang, Junfeng Jiang, Chandrajit Bajaj
Our approach builds on an approximation of the as-rigid-as possible (or ARAP) deformation energy.
no code implementations • NeurIPS 2020 • Xiangru Huang, Haitao Yang, Etienne Vouga, QiXing Huang
We introduce an approach for establishing dense correspondences between partial scans of human models and a complete template model.
1 code implementation • 16 May 2019 • Zaiwei Zhang, Xiangru Huang, Qi-Xing Huang, Xiao Zhang, Yuan Li
We formulate this problem as joint learning of multiple copies of the same network architecture and enforce the network weights to be shared across these networks.
1 code implementation • CVPR 2019 • Xiangru Huang, Zhenxiao Liang, Xiaowei Zhou, Yao Xie, Leonidas Guibas, Qi-Xing Huang
Our approach alternates between transformation synchronization using weighted relative transformations and predicting new weights of the input relative transformations using a neural network.
no code implementations • ECCV 2018 • Yifan Sun, Zhenxiao Liang, Xiangru Huang, Qi-Xing Huang
Most existing techniques in map computation (e. g., in the form of feature or dense correspondences) assume that the underlying map between an object pair is unique.
no code implementations • NeurIPS 2017 • Xiangru Huang, Zhenxiao Liang, Chandrajit Bajaj, Qi-Xing Huang
In this paper, we introduce a robust algorithm, \textsl{TranSync}, for the 1D translation synchronization problem, in which the aim is to recover the global coordinates of a set of nodes from noisy measurements of relative coordinates along an observation graph.
no code implementations • NeurIPS 2016 • Ian En-Hsu Yen, Xiangru Huang, Kai Zhong, Ruohan Zhang, Pradeep K. Ravikumar, Inderjit S. Dhillon
In this work, we show that, by decomposing training of Structural Support Vector Machine (SVM) into a series of multiclass SVM problems connected through messages, one can replace expensive structured oracle with Factorwise Maximization Oracle (FMO) that allows efficient implementation of complexity sublinear to the factor domain.
1 code implementation • ICML 2016 • Ian En-Hsu Yen, Xiangru Huang, Pradeep Ravikumar, Kai Zhong, Inderjit S. Dhillon
In this work, we show that a margin-maximizing loss with l1 penalty, in case of Extreme Classification, yields extremely sparse solution both in primal and in dual without sacrificing the expressive power of predictor.