Deep single image manipulation using conditional adversarial generators! For pro
Deep Learning/Papers2read 2020. 7. 8. 16:16Deep single image manipulation using conditional adversarial generators!
For project and code/API/dataset requests: https://www.catalyzex.com/paper/arxiv:2007.01289
Their network learns to map between a primitive representation of the image (e.g. edges) to the image itself. At manipulation time, their generator allows for making general image changes by modifying the primitive input representation and mapping it through the network.
