Xiaodong Gu
Alibaba Group
8 Papers
1 Citations
Xiaodong Gu is an academic researcher from Alibaba Group. The author has contributed to research in topics: Computer science & Motion estimation. The author has an hindex of 6, co-authored 8 publications. Previous affiliations of Xiaodong Gu include Harbin Institute of Technology.
Chat about Author
Papers
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
Xiaodong Gu,Zhiwen Fan,Siyu Zhu,Zuozhuo Dai,Feitong Tan,Ping Tan +5 more
- 14 Jun 2020
TL;DR: This paper proposes a both memory and time efficient cost volume formulation that is complementary to existing multi-view stereo and stereo matching approaches based on 3D cost volumes and applies the cascade cost volume to the representative MVS-Net, obtaining a 35.6% improvement on DTU benchmark.
Batch DropBlock Network for Person Re-Identification and Beyond
Zuozhuo Dai,Mingqiang Chen,Xiaodong Gu,Siyu Zhu,Ping Tan +4 more
- 01 Oct 2019
TL;DR: The Batch DropBlock (BDB) Network is a two branch network composed of a conventional ResNet-50 as the global branch and a feature dropping branch that achieves state-of-the-art on person re-identification and it is also applicable to general metric learning tasks.
•Posted Content
Batch DropBlock Network for Person Re-identification and Beyond
TL;DR: BDB as discussed by the authors proposes a two-branch network composed of a conventional ResNet-50 as the global branch and a feature dropping branch, which randomly drops the same region of all input feature maps in a batch to reinforce the attentive feature learning of local regions.
194
•Posted Content
Landmark Assisted CycleGAN for Cartoon Face Generation
TL;DR: This paper proposes landmark assisted CycleGAN, which utilizes face landmarks to define landmark consistency loss and to guide the training of local discriminator in CycleGAN to enforce structural consistency in landmarks, and utilizes the conditional generator and discriminator.
44
•Posted Content
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
TL;DR: In this paper, the authors proposed a cost volume formulation that is complementary to existing multi-view stereo and stereo matching approaches based on 3D cost volumes, and applied the cascade cost volume to the representative MVS-Net, and obtained a 23.1% improvement on DTU benchmark.
23