Research map / Image generation / Editing and style transfer
Not Just Compete, but Collaborate: Local Image-to-Image Translation via Cooperative Mask Prediction
Daejin Kim, Mohammad Azam Khan, Jaegul Choo
Check 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 CAM-consistency loss to StarGAN | StarGAN · CelebA, 13 translation tasks | FID: 21.14 (±6.77) -> 17.98 (±3.24) | Improved |
| Add CAM-consistency loss to AttGAN | AttGAN · CelebA, 13 translation tasks | FID: 14.27 (±6.29) -> 13.27 (±4.04) | Improved |
| Add CAM-consistency loss to STGAN | STGAN · CelebA, 13 translation tasks | FID: 11.61 (±4.68) -> 10.49 (±3.66) | Improved |
| Add CAM-consistency loss to StarGAN | StarGAN · CelebA, average of four attributes | PSNR: 23.25 -> 25.66 | Improved |
| Add CAM-consistency loss to AttGAN | AttGAN · CelebA, average of four attributes | PSNR: 27.26 -> 28.47 | Improved |
| Add CAM-consistency loss to STGAN | STGAN · CelebA, average of four attributes | PSNR: 26.15 -> 28.27 | Improved |
| Apply CAM-consistency loss only to the generator (ablation) | AttGAN · CelebA facial attribute editing | attribute editing and preservation quality | Hurt |
| Apply CAM-consistency loss only to the discriminator (ablation) | AttGAN · CelebA facial attribute editing | attribute editing and preservation quality | Mixed |
| Apply CAM-consistency loss to both generator and discriminator (ablation) | AttGAN · CelebA facial attribute editing | attribute editing and preservation quality | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- StarGAN — StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (CVPR 2018) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Image-to-Image Translation With Disentangled Latent Vectors for Face Editing (TPAMI 2023 · similarity 0.88)
- CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing (ECCV 2020 · similarity 0.88)
- Unpaired Image-to-Image Translation using Adversarial Consistency Loss (ECCV 2020 · similarity 0.88)
- SDGAN: Disentangling Semantic Manipulation for Facial Attribute Editing (AAAI 2024 · similarity 0.85)
- CA-Edit: Causality-Aware Condition Adapter for High-Fidelity Local Facial Attribute Editing (AAAI 2025 · similarity 0.85)
- CAMILA: Context-Aware Masking for Image Editing with Language Alignment (NeurIPS 2025 · similarity 0.85)
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.
