publications

2024

  1. Vision
    tang2024mvdiffusion.gif
    MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction
    Shitao Tang, Jiacheng Chen, Dilin Wang, Chengzhou Tang, Fuyang Zhang, Yuchen Fan, Vikas Chandra, Yasutaka Furukawa, and Rakesh Ranjan
    In European Conference on Computer Vision (ECCV), 2024
  2. Vision
    gu2024dro.png
    DRO: Deep Recurrent Optimizer for Video to Depth
    Xiaodong Gu, Weihao Yuan, Zuozhuo Dai, Siyu Zhu, Chengzhou Tang, Zilong Dong, and Ping Tan
    IEEE Robotics and Automation Letters (RA-L), 2024

2022

  1. Vision
    tang2022zoom.png
    Learning to Zoom Inside Camera Pipeline
    Chengzhou Tang, Yuqiang Yang, Bing Zeng, Ping Tan, and Shuaicheng Liu
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  2. Vision
    gu2022recurrent.png
    Recurrent Closest Point for Point Clouds
    Xiaodong Gu, Chengzhou Tang, Zhuozuo Dai, Siyu Zhu, and Ping Tan
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

2021

  1. Vision
    tang2021dsm.png
    DSM: Dense Scene Matching for Camera Localization
    Shitao Tang, Chengzhou Tang, Rui Huang, Siyu Zhu, and Ping Tan
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

2020

  1. Vision
    tang2020lsm.gif
    LSM: Learning Subspace Minimization for Low-level Vision
    Chengzhou Tang, Lu Yuan, and Ping Tan
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020

2019

  1. Vision
    yang2019sanet.png
    SANet: Scene Agnostic Network for Camera Localization
    Luwei Yang, Ziqian Bai, Chengzhou Tang, Honghua Li, Yasutaka Furukawa, and Ping Tan
    In IEEE International Conference on Computer Vision (ICCV), 2019
  2. Vision
    tang2019banet.png
    BA-Net: Dense Bundle Adjustment Networks
    Chengzhou Tang, and Ping Tan
    In International Conference on Learning Representations (ICLR), 2019
  3. Graphics
    tang2019tog.jpeg
    Joint Direction and Stabilization for 360° Videos
    Chengzhou Tang, Oliver Wang, Feng Liu, and Ping Tan
    ACM Transactions on Graphics (TOG), 2019

2017

  1. Vision
    tang2017gslam.png
    GSLAM: Initialization-robust Monocular Visual SLAM via Global Structure-from-Motion
    Chengzhou Tang, Oliver Wang, and Ping Tan
    In International Conference on 3D Vision (3DV), 2017

2015

  1. Vision
    cui2015linear.png
    Linear Global Translation Estimation with Feature Tracks
    Zhaopeng Cui, Nianjuan Jiang, Chengzhou Tang, and Ping Tan
    In British Machine Vision Conference (BMVC), 2015

2014

  1. Multimedia
    tang2014local.png
    Local Subspace Video Stabilization
    Chengzhou Tang, and Ronggang Wang
    In IEEE International Conference on Multimedia & Expo (ICME), 2014
  2. Multimedia
    tang2014sparse.png
    Sparse Moving Factorization for Subspace Video Stabilization
    Chengzhou Tang, and Ronggang Wang
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014

2013

  1. Multimedia
    tang2013adaptive.png
    Adaptive Motion Estimation Order for Frame Rate Up-conversion
    Chengzhou Tang, Ronggang Wang, and Wenmin Wang
    In IEEE International Symposium on Circuits and Systems (ISCAS), 2013