Research map / Image generation / GANs
CollaGAN: Collaborative GAN for Missing Image Data Imputation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 multiple-cycle consistency instead of direct L1 regression (ablation) | CollaGAN · RaFD | NMSE: 0.0372±0.00653 -> 0.0178±0.00419 | Helped |
| Use multiple-cycle consistency instead of direct L1 regression (ablation) | CollaGAN · RaFD | SSIM: 0.714±0.0211 -> 0.793±0.0237 | Helped |
| Add SSIM loss (ablation) | CollaGAN · RaFD | NMSE: 0.0200±0.00391 -> 0.0178±0.00419 | Helped |
| Add SSIM loss (ablation) | CollaGAN · RaFD | SSIM: 0.779±0.0243 -> 0.793±0.0237 | Helped |
| Add random input dropout (randomly null input images) (ablation) | CollaGAN · RaFD facial expression imputation | reconstruction quality | Helped |
| Provide more available input images (ablation) | CollaGAN · RaFD facial expression imputation | reconstruction quality | Helped |
| Use collaborative multiple-image inputs instead of a single input | CollaGAN · MR contrast, illumination, and facial expression imputation | NMSE and SSIM | Helped |
| Substitute an unavailable input with another subject’s image (ablation) | CollaGAN · RaFD incomplete-input imputation | visual reconstruction quality | No clear effect |
Closest papers by meaning
- GAMIN: Generative Adversarial Multiple Imputation Network for Highly Missing Data (CVPR 2020 · similarity 0.91)
- GAIN: Missing Data Imputation using Generative Adversarial Nets (ICML 2018 · similarity 0.90)
- MisGAN: Learning from Incomplete Data with Generative Adversarial Networks (ICLR 2019 · similarity 0.89)
- Missing Data Imputation by Reducing Mutual Information with Rectified Flows (NeurIPS 2025 · similarity 0.86)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.84)
- RG-GAN: Dynamic Regenerative Pruning for Data-Efficient Generative Adversarial Networks (AAAI 2024 · similarity 0.83)
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.