Self-Attention Generative Adversarial Networks
- Han Zhang, Ian J. Goodfellow, Dimitris N. Metaxas, Augustus Odena
- Computer ScienceInternational Conference on Machine Learning
- 21 May 2018
The proposed SAGAN achieves the state-of-the-art results, boosting the best published Inception score from 36.8 to 52.52 and reducing Frechet Inception distance from 27.62 to 18.65 on the challenging ImageNet dataset.
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
- Han Zhang, Tao Xu, Dimitris N. Metaxas
- Computer ScienceIEEE International Conference on Computer Vision
- 10 December 2016
This paper proposes Stacked Generative Adversarial Networks (StackGAN) to generate 256 photo-realistic images conditioned on text descriptions and introduces a novel Conditioning Augmentation technique that encourages smoothness in the latent conditioning manifold.
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
- Han Zhang, Tao Xu, Dimitris N. Metaxas
- Computer ScienceIEEE Transactions on Pattern Analysis and Machineā¦
- 19 October 2017
Extensive experiments demonstrate that the proposed stacked generative adversarial networks significantly outperform other state-of-the-art methods in generating photo-realistic images.
A Level Set Method for Image Segmentation in the Presence of Intensity Inhomogeneities With Application to MRI
- Chunming Li, Rui Huang, Z. Ding, C. Gatenby, Dimitris N. Metaxas, J. Gore
- MathematicsIEEE Transactions on Image Processing
- 1 July 2011
A novel region-based method for image segmentation, which is able to simultaneously segment the image and estimate the bias field, and the estimated bias field can be used for intensity inhomogeneity correction (or bias correction).
Engineering and algorithm design for an image processing Api: a technical report on ITK--the Insight Toolkit.
- T. Yoo, M. Ackerman, R. Whitaker
- Computer ScienceStudies in Health Technology and Informatics
- 2002
We present the detailed planning and execution of the Insight Toolkit (ITK), an application programmers interface (API) for the segmentation and registration of medical image data. This publicā¦
Realistic Animation of Liquids
- N. Foster, Dimitris N. Metaxas
- PhysicsGraphics Interface
- 1 May 1996
This approach unifies existing computer graphics techniques for simulating fluids and extends them by incorporating more complex behavior based on the NavierāStokes equations which couple momentum and mass conservation to completely describe fluid motion.
Semantic Graph Convolutional Networks for 3D Human Pose Regression
- Long Zhao, Xi Peng, Yu Tian, Mubbasir Kapadia, Dimitris N. Metaxas
- Computer ScienceComputer Vision and Pattern Recognition
- 6 April 2019
The proposed Semantic Graph Convolutional Networks (SemGCN), a novel neural network architecture that operates on regression tasks with graph-structured data that learns to capture semantic information such as local and global node relationships, which is not explicitly represented in the graph.
Learning with structured sparsity
- Junzhou Huang, Tong Zhang, Dimitris N. Metaxas
- Computer ScienceInternational Conference on Machine Learning
- 17 March 2009
This paper investigates a new learning formulation called structured sparsity, which is a natural extension of the standard sparsity concept in statistical learning and compressive sensing. Byā¦
Multispectral Deep Neural Networks for Pedestrian Detection
- Jingjing Liu, Shaoting Zhang, Shu Wang, Dimitris N. Metaxas
- Computer ScienceBritish Machine Vision Conference
- 8 November 2016
This work carefully design four ConvNet fusion architectures that integrate two-branch ConvNets on different DNNs stages, all of which yield better performance compared with the baseline detector, and finds that ConvNet-based pedestrian detectors trained by color or thermal images separately provide complementary information in discriminating human instances.
Handling Noise in Single Image Deblurring Using Directional Filters
- Lin Zhong, Sunghyun Cho, Dimitris N. Metaxas, Sylvain Paris, Jue Wang
- Computer ScienceIEEE Conference on Computer Vision and Patternā¦
- 23 June 2013
This work proposes a new method for handling noise in blind image deconvolution based on new theoretical and practical insights, and observes that applying a directional low-pass filter to the input image greatly reduces the noise level, while preserving the blur information in the orthogonal direction to the filter.
...
...