ECCV 2020 paper: "GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation"
An unsupervised image-to-image translation network that transforms images gradually between two domains, through multiple hops. Instead of executing translation directly, we steer the translation by requiring the network to produce in-between images which resemble weighted hybrids between images from the two input domains. Our network is trained on unpaired images from the two domains only, without any in-between images. All hops are produced using a single generator along each direction.
GANHopper excels at learning translations that involve shape domain-specific image features and geometric variations (e.g., dogs to cats) while also preserving non-domain-specific features such as general color schemes.
Видео ECCV 2020 paper: "GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation" канала Hao Zhang
GANHopper excels at learning translations that involve shape domain-specific image features and geometric variations (e.g., dogs to cats) while also preserving non-domain-specific features such as general color schemes.
Видео ECCV 2020 paper: "GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation" канала Hao Zhang
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![[ECCV 2020] demo submit A Large Multiview Dataset of Human Body Expressions and Benchmark Challeng](https://i.ytimg.com/vi/tjNJ7Nm5_pk/default.jpg)
![Deformable Style Transfer (ECCV 2020) - 10min Talk](https://i.ytimg.com/vi/mVU5tSxS4is/default.jpg)
![[ECCV 2020] Flow-edge Guided Video Completion](https://i.ytimg.com/vi/CHHVPxHT7rc/default.jpg)
![Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections - ECCV2020](https://i.ytimg.com/vi/QBOze0rP3uY/default.jpg)
![[ECCV 2020] Towards Streaming Perception](https://i.ytimg.com/vi/x6AJnk2ph00/default.jpg)
![Synthesis of High-Quality Face Videos (CVPR 2020)](https://i.ytimg.com/vi/KRB4SNdqjRk/default.jpg)
![HTML: A Parametric Hand Texture Model for 3D Hand Reconstruction and Personalization (ECCV 2020)](https://i.ytimg.com/vi/bKGRr01RG10/default.jpg)
![DIL workshop, ECCV 2020](https://i.ytimg.com/vi/tjxII31RegQ/default.jpg)
![Sea-thru ECCV2020 DEMO](https://i.ytimg.com/vi/O7s2Yw7WFRs/default.jpg)
![[ECCV 2020] BroadFace : Face Recognition](https://i.ytimg.com/vi/p9y-gOkWgmU/default.jpg)
![DETR - End to end object detection with transformers (ECCV2020)](https://i.ytimg.com/vi/utxbUlo9CyY/default.jpg)
![TilinGNN: Learning to Tile with Self-Supervised Graph Neural Network (SIGGRAPH 2020)](https://i.ytimg.com/vi/doUZXYPTSi8/default.jpg)
![Beyond 2D Visual Recognition (CVPR 2020)](https://i.ytimg.com/vi/1tcQw9oszPY/default.jpg)
![I2L-MeshNet (3D Human Pose and Mesh Estimation. ECCV 2020)](https://i.ytimg.com/vi/vIF9s71QrP0/default.jpg)
![Webinar 04 - Setting the eCenters as Tool for Development](https://i.ytimg.com/vi/Leyg5QeT6K4/default.jpg)
![[ECCV 2020 10min] Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild](https://i.ytimg.com/vi/b2IdzUe2hxI/default.jpg)
![[ECCV 2020] Few Shot Object Detection and Viewpoint Estimation Long Video](https://i.ytimg.com/vi/3WU-pb7VrMU/default.jpg)