Research
I'm currently conducting research in 3D Vision with Prof. Jan-Michael Frahm. And I mainly focus on research topics related to dynamic scene reconstruction.
Before here, I spent three years in Institute of Computing Technology, CAS, Beijing where I study for my master degree and worked on facial animation related projects.
Publications
-
Spatio-Temporally Consistent Correspondence for Dense Dynamic Scene Modeling,
Dinghuang Ji, Enrique Dunn, Jan-Michael Frahm
In ECCV 2016, accepted as poster [Paper] -
Self-expressive Dictionary Learning for Dynamic 3D Reconstruction,
Enliang Zheng, Dinghuang Ji,, Enrique Dunn and Jan-Michael Frahm
Journal version of the ICCV paper [Paper] -
From Dusk Till Dawn: Modeling in the Dark,
Filip Radenovic, Johannes Schonberger, Dinghuang Ji, Jan-Michael Frahm, Ondrej Chum, Jiri Maras
In CVPR 2016, accepted as spotlight [Paper] -
Synthesizing Illumination Mosaics from Internet Photo-Collections,
Dinghuang Ji, Enrique Dunn and Jan-Michael Frahm
In ICCV 2015, accepted as poster [Paper] [Demo] -
Sparse Dynamic 3D Reconstruction from Unsynchronized Videos,
Enliang Zheng, Dinghuang Ji,, Enrique Dunn and Jan-Michael Frahm
In ICCV 2015, accepted as poster -
3D Reconstruction of Dynamic Textures in Crowd Sourced Data,
Dinghuang Ji, Enrique Dunn and Jan-Michael Frahm
In ECCV 2014, accepted as poster [Paper] [Demo] [Poster] [Codes] [Datasets] -
Towards Accurately Extracting Facial Expression Parameters,
Xuecheng Liu,Dinghuang Ji, Zhaoqi Wang and Shihong Xia
In Proceedings of Asian Conference on Design and Digital Engineering 2011, Regular Paper Volume, pages 329 - 336 [pdf] [slides] -
Intelligent Photo Clustering with User Interaction and Distance Metric Learning ,
Meng Wang,Dinghuang Ji, Qi Tian and Xiansheng Hua
Pattern Recognition Letters (17 February 2011) [pdf] [slides] -
Semi-Automatic Photo Clustering with Distance Metric Learning , Dinghuang
Ji, Meng Wang, Xiansheng Hua and Qi Tian,
Proceedings of the SPIE, Volume 7744, 2010 [pdf] [slides] [code] -
Expression Cloning based on Deformation Transfer, Dinghuang
Ji, Supervised by : Shihong Xia,
Master degree Thesis, Institute of Computing Technology, CAS. Jun 2012. [pdf] -
Implementation of Some Key Technologies in Virtual 3D Community, Dinghuang
Ji, Supervised by : Chenxi Shao, Zhaoqi Wang,
Undergraduate Thesis, Computer Science and Technology Department, USTC. Jun 2009. [pdf] -
Wright Eagle 2008 3D team description paper., Xue Feng, Tai Yunfang, Xie Jiongkun, Zhou Weimin, Ji Dinghuang, Zhang Zhiqiang and Xiaoping Chen
Proceedings CD of RoboCup 2008, 2008.
Errata
Errata: A reference is missed in the Springer version of ECCV 2014 paper, I want to say sorry to the author Dr. Changchang Wu and the reference is: Wu, C.: Towards linear-time incremental structure from motion. 3DV-Conference (2013)