Jun-Yan Zhu, David Bau, Sheng-Yu Wang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Can a user create a deep generative model by sketching a single example? Traditionally, creating a GAN model has required the collection of a large-scale dataset of exemplars and specialized knowledge in deep learning. In contrast, sketching is possibly the most universally accessible way to convey a visual concept. In this work, we present a method, GAN Sketching, for rewriting GANs with one or more sketches, to make GANs training easier for novice users. In particular, we change the weights of an original GAN model according to user sketches. We encourage the model's output to match the user sketches through a crossdomain adversarial loss. Furthermore, we explore different regularization methods to preserve the original model's diversity and image quality. Experiments have shown that our method can mold GANs to match shapes and poses specified by sketches while maintaining realism and diversity. Finally, we demonstrate a few applications of the resulting GAN, including latent space interpolation and image editing.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2108.02774")
get_code_for_paper("2108.02774")
have("2108.02774")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2108.02774.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2108.02774)
Connect an agent — have() is free.