Research map / Image generation / Editing and style transfer
Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors
Qi Mao, Hung-Yu Tseng, Hsin-Ying Lee, Jia‐Bin Huang, Siwei Ma, Ming–Hsuan Yang
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 |
|---|---|---|---|
| add the sign operation to attribute vectors (signed attribute vectors) (ablation) | Ours · CelebA-HQ male-to-female | translation ACC | Improved |
| add reverse sign domain adversarial loss (ablation) | Ours · CelebA-HQ male-to-female | DIPD and LPIPS | Improved |
| add interpolated domain adversarial loss (ablation) | Ours · CelebA-HQ male-to-female | FID and LPIPS | Improved |
| add style reconstruction loss (ablation) | Ours · CelebA-HQ male-to-female | FID | Improved |
| add fusing network before the generator (ablation) | Ours · CelebA-HQ male-to-female | FID | Improved |
| add MMD constraint on attribute vectors (ablation) | Ours · CelebA-HQ male-to-female / AFHQ wildlife | ACC, FID, DIPD, LPIPS smoothness | Mixed |
| replace StarGAN-v2 separate per-domain attribute spaces with signed attribute vectors | Ours vs StarGAN-v2 · CelebA-HQ and AFHQ | smoothness of LPIPS curve | Improved |
| use larger batch size for FUNIT | FUNIT · CelebA-HQ | realism preference: 82.50 -> 83.75 | Improved |
Closest papers by meaning
- Domain Adaptive Image-to-Image Translation (CVPR 2020 · similarity 0.87)
- Multi-mapping Image-to-Image Translation via Learning Disentanglement (NeurIPS 2019 · similarity 0.87)
- Bridging the Gap Between Label- and Reference-Based Synthesis in Multi-Attribute Image-to-Image Translation (ICCV 2021 · similarity 0.87)
- Homomorphic Latent Space Interpolation for Unpaired Image-To-Image Translation (CVPR 2019 · similarity 0.87)
- TransferI2I: Transfer Learning for Image-to-Image Translation From Small Datasets (ICCV 2021 · similarity 0.87)
- Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation (CVPR 2021 · similarity 0.86)
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.
