no code implementations • 3 Apr 2024 • Su Sun, Cheng Zhao, Yuliang Guo, Ruoyu Wang, Xinyu Huang, Yingjie Victor Chen, Liu Ren
The 3D Inpainter with abstract representation at coarse levels is trained offline using various scenes to complete occluded surfaces.
no code implementations • 3 Apr 2024 • Cheng Zhao, Su Sun, Ruoyu Wang, Yuliang Guo, Jun-Jun Wan, Zhou Huang, Xinyu Huang, Yingjie Victor Chen, Liu Ren
Most 3D Gaussian Splatting (3D-GS) based methods for urban scenes initialize 3D Gaussians directly with 3D LiDAR points, which not only underutilizes LiDAR data capabilities but also overlooks the potential advantages of fusing LiDAR with camera data.
no code implementations • 23 Mar 2024 • Yuliang Guo, Abhinav Kumar, Cheng Zhao, Ruoyu Wang, Xinyu Huang, Liu Ren
Monocular 3D reconstruction for categorical objects heavily relies on accurately perceiving each object's pose.
1 code implementation • NeurIPS 2023 • Yunhao Ge, Hong-Xing Yu, Cheng Zhao, Yuliang Guo, Xinyu Huang, Liu Ren, Laurent Itti, Jiajun Wu
A major challenge in monocular 3D object detection is the limited diversity and quantity of objects in real datasets.
no code implementations • 19 Mar 2023 • Cheng Zhao, Shuo Yuan
In this paper, we will consider a class of continuous-time stochastic control systems with both unknown nonlinear structure and unknown disturbances, and investigate the capability of the classical proportional-integral-derivative(PID) controller in tracking time-varying reference signals.
no code implementations • 10 May 2022 • Cheng Zhao, Yanbin Zhang
In this article, we focus on the global stabilizability problem for a class of second order uncertain stochastic control systems, where both the drift term and the diffusion term are nonlinear functions of the state variables and the control variables.
no code implementations • 1 Sep 2021 • Ze Huang, Li Sun, Cheng Zhao, Song Li, Songzhi Su
We propose a new time-surface-like event stream representation method called Tencode.
1 code implementation • 23 Mar 2021 • Zhicheng Zhou, Cheng Zhao, Daniel Adolfsson, Songzhi Su, Yang Gao, Tom Duckett, Li Sun
Benefiting from the NDT representation and NDT-Transformer network, the learned global descriptors are enriched with both geometrical and contextual information.
1 code implementation • 17 Jul 2020 • Julian E. Bautista, Romain Paviot, Mariana Vargas Magaña, Sylvain de la Torre, Sebastien Fromenteau, Hector Gil-Marín, Ashley J. Ross, Etienne Burtin, Kyle S. Dawson, Jiamin Hou, Jean-Paul Kneib, Arnaud de Mattia, Will J. Percival, Graziano Rossi, Rita Tojeiro, Cheng Zhao, Gong-Bo Zhao, Shadab Alam, Joel Brownstein, Michael J. Chapman, Peter D. Choi, Chia-Hsun Chuang, Stéphanie Escoffier, Axel de la Macorra, Hélion du Mas des Bourboux, Faizan G. Mohammad, Jeongin Moon, Eva-Maria Müller, Seshadri Nadathur, Jeffrey A. Newman, Donald Schneider, Hee-Jong Seo, Yuting Wang
We present the cosmological analysis of the configuration-space anisotropic clustering in the completed Sloan Digital Sky Survey IV (SDSS-IV) extended Baryon Oscillation Spectroscopic Survey (eBOSS) DR16 galaxy sample.
Cosmology and Nongalactic Astrophysics
no code implementations • 17 Jul 2020 • Santiago Avila, Violeta Gonzalez-Perez, Faizan G. Mohammad, Arnaud de Mattia, Cheng Zhao, Anand Raichoor, Amelie Tamone, Shadab Alam, Julian Bautista, Davide Bianchi, Etienne Burtin, Michael J. Chapman, Chia-Hsun Chuang, Johan Comparat, Kyle Dawson, Thomas Divers, Helion du Mas des Bourboux, Hector Gil-Marin, Eva-Maria Mueller, Salman Habib, Katrin Heitmann, Vanina Ruhlmann-Kleider, Nelson Padilla, Will J. Percival, Ashley J. Ross, Hee-Jong Seo, Donald P. Schneider, Gong-Bo Zhao
We study how these choices impact the clustering statistics while keeping the number density and bias fixed to that from eBOSS ELGs.
Cosmology and Nongalactic Astrophysics Astrophysics of Galaxies
1 code implementation • 17 Jul 2020 • Gong-Bo Zhao, Yuting Wang, Atsushi Taruya, Weibing Zhang, Hector Gil-Marin, Arnaud de Mattia, Ashley J. Ross, Anand Raichoor, Cheng Zhao, Will J. Percival, Shadab Alam, Julian E. Bautista, Etienne Burtin, Chia-Hsun Chuang, Kyle S. Dawson, Jean-Paul Kneib, Kazuya Koyama, Helion du Mas des Bourboux, Eva-Maria Mueller, Jeffrey A. Newman, John A. Peacock, Graziano Rossi, Vanina Ruhlmann-Kleider, Donald P. Schneider, Arman Shafieloo
We perform a joint BAO and RSD analysis using the eBOSS DR16 LRG and ELG samples in the redshift range of $z\in[0. 6, 1. 1]$, and detect a RSD signal from the cross power spectrum at a $\sim4\sigma$ confidence level, i. e., $f\sigma_8=0. 317\pm0. 080$ at $z_{\rm eff}=0. 77$.
Cosmology and Nongalactic Astrophysics
1 code implementation • 17 Jul 2020 • Yuting Wang, Gong-Bo Zhao, Cheng Zhao, Oliver H. E. Philcox, Shadab Alam, Amélie Tamone, Arnaud de Mattia, Ashley J. Ross, Anand Raichoor, Etienne Burtin, Romain Paviot, Sylvain de la Torre, Will J. Percival, Kyle S. Dawson, Héctor Gil-Marín, Julian E. Bautista, Jiamin Hou, Kazuya Koyama, John A. Peacock, Vanina Ruhlmann-Kleider, Hélion du Mas des Bourboux, Johan Comparat, Stephanie Escoffier, Eva-Maria Mueller, Jeffrey A. Newman, Graziano Rossi, Arman Shafieloo, Donald P. Schneider
We perform a multi-tracer analysis using the complete Sloan Digital Sky Survey IV (SDSS-IV) extended Baryon Oscillation Spectroscopic Survey (eBOSS) DR16 luminous red galaxy (LRG) and the DR16 emission line galaxy (ELG) samples in the configuration space, and successfully detect a cross correlation between the two samples, and find the growth rate to be $f\sigma_8=0. 342 \pm 0. 085$ ($\sim25$ per cent accuracy) from the cross sample alone.
Cosmology and Nongalactic Astrophysics
1 code implementation • 21 May 2020 • Cheng Zhao, Chenliang Li, Rong Xiao, Hongbo Deng, Aixin Sun
Given two relevant domains (e. g., Book and Movie), users may have interactions with items in one domain but not in the other domain.
no code implementations • Conference 2019 • Cheng Zhao, Chenliang Li, Cong Fu
We find there are mainly three problems in their formulations: 1) their knowledge transfer is unaware of the cross-domain graph structure.
3 code implementations • 17 May 2019 • Philipp Becker, Harit Pandya, Gregor Gebhardt, Cheng Zhao, James Taylor, Gerhard Neumann
In order to integrate uncertainty estimates into deep time-series modelling, Kalman Filters (KFs) (Kalman et al., 1960) have been integrated with deep learning models, however, such approaches typically rely on approximate inference techniques such as variational inference which makes learning more complex and often less scalable due to approximation errors.
no code implementations • 2 Jul 2018 • Li Sun, Zhi Yan, Anestis Zaganidis, Cheng Zhao, Tom Duckett
Most existing semantic mapping approaches focus on improving semantic understanding of single frames, rather than 3D refinement of semantic maps (i. e. fusing semantic observations).
no code implementations • 6 Mar 2018 • Cheng Zhao, Li Sun, Pulak Purkait, Tom Duckett, Rustam Stolkin
Dense 2D flow and a depth image are generated from monocular images by sub-networks, which are then used by a 3D flow associated layer in the L-VO network to generate dense 3D flow.
1 code implementation • 9 Dec 2017 • Pulak Purkait, Cheng Zhao, Christopher Zach
In this work we design a deep neural network architecture based on sparse feature descriptors to estimate the absolute pose of an image.
no code implementations • 30 Sep 2017 • Cheng Zhao, Li Sun, Pulak Purkait, Rustam Stolkin
For intelligent robotics applications, extending 3D mapping to 3D semantic mapping enables robots to, not only localize themselves with respect to the scene's geometrical features but also simultaneously understand the higher level meaning of the scene contexts.
1 code implementation • 15 Sep 2017 • Yuting Wang, Gong-Bo Zhao, Chia-Hsun Chuang, Marcos Pellejero-Ibanez, Cheng Zhao, Francisco-Shu Kitaura, Sergio Rodriguez-Torres
In order to extract the redshift information of anisotropic galaxy clustering, we analyse this data set in nine overlapping redshift slices in configuration space and perform the joint constraints on the parameters $(D_V, F_{\mathrm{AP}}, f\sigma_8)$ using the correlation function multipoles.
Cosmology and Nongalactic Astrophysics
1 code implementation • 19 Mar 2017 • Li Sun, Cheng Zhao, Rustam Stolkin
We also propose a novel way to pretrain a DCNN for the depth modality, by training on virtual depth images projected from CAD models.
no code implementations • 14 Mar 2017 • Cheng Zhao, Li Sun, Rustam Stolkin
We present the results of experiments, in which we trained our system to perform real-time 3D semantic reconstruction for 23 different materials in a real-world application.