Rongrong Ji, Yongjian Wu, Jie Hu, Xinyang Li, Feiyue Huang, Liujuan Cao, Xudong Mao, Shengchuan Zhang, Hong Xiaopeng, With_Glasses Blond_Hair, Black_Hair With_Bangs
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.
Recently, image-to-image translation has made significant progress in achieving both multi-label (i.e., translation conditioned on different labels) and multi-style (i.e., generation with diverse styles) tasks. However, due to the unexplored independence and exclusiveness in the labels, existing endeavors are defeated by involving uncontrolled manipulations to the translation results. In this paper, we propose Hierarchical Style Disentanglement (HiSD) to address this issue. Specifically, we organize the labels into a hierarchical tree structure, in which independent tags, exclusive attributes, and disentangled styles are allocated from top to bottom. Correspondingly, a new translation process is designed to adapt the above structure, in which the styles are identified for controllable translations. Both qualitative and quantitative results on the CelebA-HQ dataset verify the ability of the proposed HiSD. The code has been released at https://github.com/imlixinyang/HiSD.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.01456")
get_code_for_paper("2103.01456")
have("2103.01456")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.01456.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.01456)
Connect an agent — have() is free.