paper-with-me

홈 › Papers

Improving Shape Deformation in Unsupervised Image-to-Image Translation

2018-08-13 · ECCV 2018 9 · Aaron Gokaslan, Vivek Ramanujan, Daniel Ritchie, Kwang In Kim, James Tompkin

Unsupervised image-to-image translation techniques are able to map local texture between two domains, but they are typically unsuccessful when the domains require larger shape change. Inspired by semantic segmentation, we introduce a discriminator with dilated convolutions that is able to use information from across the entire image to train a more context-aware generator. This is coupled with a multi-scale perceptual loss that is better able to represent error in the underlying shape of objects. We demonstrate that this design is more capable of representing shape deformation in a challenging toy dataset, plus in complex mappings with significant dataset variation between humans, dolls, and anime faces, and between cats and dogs.

📄 PDF Abstract BibTeX arXiv:1808.04325

Code (4)

brownvc/ganimorph 공식 구현 tf
Funaizhang/dics
advaitrane/GANimorph_pytorch pytorch
itsss/ganimorph tf

Tasks

Image-to-Image TranslationSemantic SegmentationTranslationUnsupervised Image-To-Image Translation

Similar Papers 제목 키워드 기반

Unsupervised Deformable Registration for Multi-Modal Images via Disentangled Representations

2019-03-22 · Chen Qin, Bibo Shi, Rui Liao, Tommaso Mansi 외

We propose a fully unsupervised multi-modal deformable image registration method (UMDIR), which does not require any ground truth deformation fields or any aligned multi-modal image pairs during training. Multi-modal reg…

Image RegistrationImage-to-Image TranslationMedical Image Analysis

SPatchGAN: A Statistical Feature Based Discriminator for Unsupervised Image-to-Image Translation

2021-03-30 · ICCV 2021 10 · Xuning Shao, Weidong Zhang

For unsupervised image-to-image translation, we propose a discriminator architecture which focuses on the statistical features instead of individual patches. The network is stabilized by distribution matching of key stat…

Image-to-Image TranslationTranslationUnsupervised Image-To-Image Translation

Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance

2018-06-18 · ECCV 2018 9 · Zhixin Shu, Mihir Sahasrabudhe, Alp Guler, Dimitris Samaras 외

In this work we introduce Deforming Autoencoders, a generative model for images that disentangles shape from appearance in an unsupervised manner. As in the deformable template paradigm, shape is represented as a deforma…

Unsupervised Facial Landmark Detection

Unsupervised Sketch to Photo Synthesis

2020-08-01 · ECCV 2020 8 · Runtao Liu, Qian Yu, Stella X. Yu

Humans can envision a realistic photo given a free-hand sketch that is not only spatially imprecise and geometrically distorted but also without colors and visual details. We study unsupervised sketch to photo synthesis …

DenoisingImage RetrievalRetrievalSketch-Based Image Retrieval+1

Unsupervised Multi-Modal Medical Image Registration via Discriminator-Free Image-to-Image Translation

2022-04-28 · Zekang Chen, Jia Wei, Rui Li

In clinical practice, well-aligned multi-modal images, such as Magnetic Resonance (MR) and Computed Tomography (CT), together can provide complementary information for image-guided therapies. Multi-modal image registrati…

Computed Tomography (CT)Image RegistrationImage-to-Image TranslationMedical Image Registration+1