no code implementations • 13 Feb 2024 • Matan Atzmon, Jiahui Huang, Francis Williams, Or Litany
Integrating a notion of symmetry into point cloud neural networks is a provably effective way to improve their generalization capability.
no code implementations • 6 Dec 2023 • Xuanchi Ren, Jiahui Huang, Xiaohui Zeng, Ken Museth, Sanja Fidler, Francis Williams
In addition to unconditional generation, we show that our model can be used to solve a variety of tasks such as user-guided editing, scene completion from a single scan, and text-to-3D.
no code implementations • 15 Jul 2023 • Jiahui Huang, Leonid Sigal, Kwang Moo Yi, Oliver Wang, Joon-Young Lee
We present Interactive Neural Video Editing (INVE), a real-time video editing solution, which can assist the video editing process by consistently propagating sparse frame edits to the entire video clip.
no code implementations • CVPR 2023 • Jiahui Huang, Zan Gojcic, Matan Atzmon, Or Litany, Sanja Fidler, Francis Williams
We present a novel method for reconstructing a 3D implicit surface from a large-scale, sparse, and noisy point cloud.
1 code implementation • 23 May 2023 • Hai Hu, Ziyin Zhang, Weifang Huang, Jackie Yan-Ki Lai, Aini Li, Yina Patterson, Jiahui Huang, Peng Zhang, Chien-Jer Charles Lin, Rui Wang
We introduce CoLAC - Corpus of Linguistic Acceptability in Chinese, the first large-scale acceptability dataset for a non-Indo-European language.
no code implementations • ICCV 2023 • Kiyohiro Nakayama, Mikaela Angelina Uy, Jiahui Huang, Shi-Min Hu, Ke Li, Leonidas J Guibas
We propose a factorization that models independent part style and part configuration distributions and presents a novel cross-diffusion network that enables us to generate coherent and plausible shapes under our proposed factorization.
no code implementations • 21 Feb 2023 • Anran Li, Hongyi Peng, Lan Zhang, Jiahui Huang, Qing Guo, Han Yu, Yang Liu
Vertical Federated Learning (VFL) enables multiple data owners, each holding a different subset of features about largely overlapping sets of data sample(s), to jointly train a useful global model.
1 code implementation • 25 Jul 2022 • Shengyu Huang, Zan Gojcic, Jiahui Huang, Andreas Wieser, Konrad Schindler
Compared to state-of-the-art scene flow estimators, our proposed approach aims to align all 3D points in a common reference frame correctly accumulating the points on the individual objects.
no code implementations • 25 Nov 2021 • Haoxiang Chen, Jiahui Huang, Tai-Jiang Mu, Shi-Min Hu
We present CIRCLE, a framework for large-scale scene completion and geometric refinement based on local implicit signed distance functions.
1 code implementation • 25 Nov 2021 • Jiahui Huang, Tolga Birdal, Zan Gojcic, Leonidas J. Guibas, Shi-Min Hu
We present SyNoRiM, a novel way to jointly register multiple non-rigid shapes by synchronizing the maps relating learned functions defined on the point clouds.
no code implementations • 24 Nov 2021 • Jiahui Huang, Yuhe Jin, Kwang Moo Yi, Leonid Sigal
In the first stage, with the rich set of losses and dynamic foreground size prior, we learn how to separate the frame into foreground and background layers and, conditioned on these layers, how to generate the next frame using VQ-VAE generator.
1 code implementation • 4 Jun 2021 • Shi-Min Hu, Zheng-Ning Liu, Meng-Hao Guo, Jun-Xiong Cai, Jiahui Huang, Tai-Jiang Mu, Ralph R. Martin
Meshes with arbitrary connectivity can be remeshed to have Loop subdivision sequence connectivity via self-parameterization, making SubdivNet a general approach.
1 code implementation • CVPR 2021 • Jiahui Huang, He Wang, Tolga Birdal, Minhyuk Sung, Federica Arrigoni, Shi-Min Hu, Leonidas Guibas
We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds.
1 code implementation • CVPR 2021 • Jiahui Huang, Shi-Sheng Huang, Haoxuan Song, Shi-Min Hu
Previous online 3D dense reconstruction methods struggle to achieve the balance between memory storage and surface quality, largely due to the usage of stagnant underlying geometry representation, such as TSDF (truncated signed distance functions) or surfels, without any knowledge of the scene priors.
2 code implementations • ECCV 2020 • Kshitij Dwivedi, Jiahui Huang, Radoslaw Martin Cichy, Gemma Roig
In this paper, we tackle an open research question in transfer learning, which is selecting a model initialization to achieve high performance on a new task, given several pre-trained models.
no code implementations • CVPR 2020 • Jiahui Huang, Sheng Yang, Tai-Jiang Mu, Shi-Min Hu
We present ClusterVO, a stereo Visual Odometry which simultaneously clusters and estimates the motion of both ego and surrounding rigid clusters/objects.
no code implementations • 22 Feb 2020 • Yinyu Nie, Shihui Guo, Jian Chang, Xiaoguang Han, Jiahui Huang, Shi-Min Hu, Jian Jun Zhang
Particularly, we design a shallow-to-deep architecture on the basis of convolutional networks for semantic scene understanding and modeling.
no code implementations • ICCV 2019 • Jiahui Huang, Sheng Yang, Zishuo Zhao, Yu-Kun Lai, Shi-Min Hu
We present a practical backend for stereo visual SLAM which can simultaneously discover individual rigid bodies and compute their motions in dynamic environments.
no code implementations • 22 Apr 2019 • Jiahui Huang, Kshitij Dwivedi, Gemma Roig
Convolutional Neural Networks (CNNs) have been proven to be extremely successful at solving computer vision tasks.
2 code implementations • 12 Jan 2019 • Jun Gao, Chengcheng Tang, Vignesh Ganapathi-Subramanian, Jiahui Huang, Hao Su, Leonidas J. Guibas
Reconstruction of geometry based on different input modes, such as images or point clouds, has been instrumental in the development of computer aided design and computer graphics.