Haitian Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Haitian Zheng has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
Connelly Barnes
Adobe Research
1 shared publicationEli Shechtman
Adobe Research
1 shared publicationJianming Zhang
Adobe Research
1 shared publicationJiebo Luo
University of Rochester
1 shared publicationJingwan Lu
Adobe Research
1 shared publicationLu Fang
The Hong Kong University of Science and Technology, Hong Kong
1 shared publication
Latest Publications
- 21 October 2022
- Published by Springer Nature
- p. 277-296
Image Inpainting with Cascaded Modulation GAN and Object-Aware Training
- 21 October 2022
- Published by Springer Nature
- p. 277-296
Image Inpainting with Cascaded Modulation GAN and Object-Aware Training
- 15 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 28 (1) , 46-61
Computation and Memory Efficient Image Segmentation
In this paper, we address the segmentation problem under limited computation and memory resources. Given a segmentation algorithm, we propose a framework that can reduce its computation time and memory requirement simultaneously, while preserving its accuracy. The proposed framework uses standard pixel-domain downsampling and includes two main steps. Coarse segmentation is first performed on the downsampled image. Refinement is then applied to the coarse segmentation results. We make two novel contributions to enable competitive accuracy using this simple framework. First, we rigorously examine the effect of downsampling on segmentation using a signal processing analysis. The analysis helps to determine the uncertain regions, which are small image regions where pixel labels are uncertain after the coarse segmentation. Second, we propose an efficient minimum spanning tree-based algorithm to propagate the labels into the uncertain regions. We perform extensive experiments using several standard data sets. The experimental results show that our segmentation accuracy is comparable to state-of-the-art methods, while requiring much less computation time and memory than those methods.
- 15 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 28 (1) , 46-61
Computation and Memory Efficient Image Segmentation
In this paper, we address the segmentation problem under limited computation and memory resources. Given a segmentation algorithm, we propose a framework that can reduce its computation time and memory requirement simultaneously, while preserving its accuracy. The proposed framework uses standard pixel-domain downsampling and includes two main steps. Coarse segmentation is first performed on the downsampled image. Refinement is then applied to the coarse segmentation results. We make two novel contributions to enable competitive accuracy using this simple framework. First, we rigorously examine the effect of downsampling on segmentation using a signal processing analysis. The analysis helps to determine the uncertain regions, which are small image regions where pixel labels are uncertain after the coarse segmentation. Second, we propose an efficient minimum spanning tree-based algorithm to propagate the labels into the uncertain regions. We perform extensive experiments using several standard data sets. The experimental results show that our segmentation accuracy is comparable to state-of-the-art methods, while requiring much less computation time and memory than those methods.