no code implementations • 24 Apr 2024 • Rui Xu, Longdu Liu, Ningna Wang, Shuangmin Chen, Shiqing Xin, Xiaohu Guo, Zichun Zhong, Taku Komura, Wenping Wang, Changhe Tu
In mesh simplification, common requirements like accuracy, triangle quality, and feature alignment are often considered as a trade-off.
no code implementations • 14 Sep 2020 • Yifan Wang, Guoli Yan, Haikuan Zhu, Sagar Buch, Ying Wang, Ewart Mark Haacke, Jing Hua, Zichun Zhong
A multi-stream convolutional neural network is proposed to learn the 3D volume and 2D MIP features respectively and then explore their inter-dependencies in a joint volume-composition embedding space by unprojecting the MIP features into 3D volume embedding space.
no code implementations • 10 May 2019 • Elaheh Barati, Xue-wen Chen, Zichun Zhong
In reinforcement learning algorithms, it is a common practice to account for only a single view of the environment to make the desired decisions; however, utilizing multiple views of the environment can help to promote the learning of complicated policies.
1 code implementation • CVPR 2019 • Artem Komarichev, Zichun Zhong, Jing Hua
Analyzing the geometric and semantic properties of 3D point clouds through the deep networks is still challenging due to the irregularity and sparsity of samplings of their geometric structures.
Ranked #35 on Semantic Segmentation on S3DIS
no code implementations • ICCV 2017 • Haotian Xu, Ming Dong, Zichun Zhong
Previous approaches on 3D shape segmentation mostly rely on heuristic processing and hand-tuned geometric descriptors.