paper-with-me

홈 › Papers

Adversarial Image Alignment and Interpolation

2017-06-30 · Viren Jain

Volumetric (3d) images are acquired for many scientific and biomedical purposes using imaging methods such as serial section microscopy, CT scans, and MRI. A frequent step in the analysis and reconstruction of such data is the alignment and registration of images that were acquired in succession along a spatial or temporal dimension. For example, in serial section electron microscopy, individual 2d sections are imaged via electron microscopy and then must be aligned to one another in order to produce a coherent 3d volume. State of the art approaches find image correspondences derived from patch matching and invariant feature detectors, and then solve optimization problems that rigidly or elastically deform series of images into an aligned volume. Here we show how fully convolutional neural networks trained with an adversarial loss function can be used for two tasks: (1) synthesis of missing or damaged image data from adjacent sections, and (2) fine-scale alignment of block-face electron microscopy data. Finally, we show how these two capabilities can be combined in order to produce artificial isotropic volumes from anisotropic image volumes using a super-resolution adversarial alignment and interpolation approach.

📄 PDF Abstract BibTeX arXiv:1707.00067

Code (0)

등록된 구현이 없습니다.

Tasks

Patch MatchingSuper-Resolution

Similar Papers 제목 키워드 기반

Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions

2018-07-17 · Tim Sainburg, Marvin Thielk, Brad Theilman, Benjamin Migliori 외

We present a neural network architecture based upon the Autoencoder (AE) and Generative Adversarial Network (GAN) that promotes a convex latent distribution by training adversarially on latent space interpolations. By us…

Generative Adversarial Network

Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Training

2026-04-29 · Yanyun Wang, Qingqing Ye, Li Liu, Zi Liang 외 arxiv

Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and adversarial robustness. In this work, we …

Adversarial Robustness

3D Registration of pre-surgical prostate MRI and histopathology images via super-resolution volume reconstruction

2021-01-23 · Medical Image Analysis 2021 1 · Rewa R. Sood, Wei Shao, Christian Kunder, Nikola C. Teslovich 외

The use of MRI for prostate cancer diagnosis and treatment is increasing rapidly. However, identifying the presence and extent of cancer on MRI remains challenging, leading to high variability in detection even among exp…

Generative Adversarial NetworkImage Super-ResolutionSuper-Resolution

Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourages convex latent distributions

2018-09-27 · Tim Sainburg, Marvin Thielk, Brad Thielman, Benjamin Migliori 외

We present a neural network architecture based upon the Autoencoder (AE) and Generative Adversarial Network (GAN) that promotes a convex latent distribution by training adversarially on latent space interpolations. By us…

Generative Adversarial Network

Harmonizing Transferability and Discriminability for Adapting Object Detectors

2020-03-13 · CVPR 2020 6 · Chaoqi Chen, Zebiao Zheng, Xinghao Ding, Yue Huang 외

Recent advances in adaptive object detection have achieved compelling results in virtue of adversarial feature adaptation to mitigate the distributional shifts along the detection pipeline. Whilst adversarial adaptation …

Objectobject-detectionObject DetectionWeakly Supervised Object Detection