Research map / Image generation / Editing and style transfer
Controllable Image Synthesis With Attribute-Decomposed GAN
Guo Pu, Yifang Men, Yiming Mao, Yuning Jiang, Wei-Ying Ma, Zhouhui Lian
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use attribute-decomposed generator instead of PATN | pose transfer · DeepFashion | IS: 3.209 -> 3.364 | Improved |
| use attribute-decomposed generator instead of PATN | pose transfer · DeepFashion | CX-GS: 2.628 -> 2.474 | Improved |
| use attribute-decomposed generator instead of PATN | pose transfer · DeepFashion | DS: 0.976 -> 0.984 | Improved |
| use attribute-decomposed generator instead of PATN | pose transfer · DeepFashion | SSIM: 0.774 -> 0.772 | No clear effect |
| use attribute-decomposed generator instead of PATN | pose transfer · DeepFashion user study | Prefer: 7.26 -> 73.55 | Improved |
| use attribute-decomposed generator instead of PATN | pose transfer · DeepFashion user study | G2R: 31.78 -> 38.67 | Improved |
| add contextual loss L_CX | Attribute-Decomposed GAN · DeepFashion | visual quality | Improved |
Closest papers by meaning
- Controllable Person Image Synthesis With Attribute-Decomposed GAN (CVPR 2020 · similarity 0.99)
- PISE: Person Image Synthesis and Editing With Decoupled GAN (CVPR 2021 · similarity 0.89)
- BodyGAN: General-Purpose Controllable Neural Human Body Generation (CVPR 2022 · similarity 0.89)
- Interpreting the Latent Space of GANs for Semantic Face Editing (CVPR 2020 · similarity 0.89)
- Cluster-Guided Image Synthesis With Unconditional Models (CVPR 2022 · similarity 0.89)
- ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes (ECCV 2018 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
