Research map / Image generation / Text-to-image diffusion
Personalized Image Generation for Color Vision Deficiency Population
Shuyi Jiang, Daochang Liu, Dingquan Li, Chang Xu
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 local contrast loss to StyleGAN (ablation) | StyleGAN · Abstract Art, protan 40% | Local contrast decay: 0.7639 -> 0.3784 | Improved |
| add color information loss to StyleGAN (ablation) | StyleGAN · Abstract Art, protan 40% | Hellinger distance: 0.0186 -> 0.0114 | Improved |
| combine local contrast and color information losses (ablation) | CVD-GAN · Abstract Art, protan 40% | Local contrast decay: 0.3784 -> 0.3355 | Improved |
| increase weight of disentanglement loss alpha (ablation) | CVD-GAN · Abstract Art | FID vs disentanglement | Mixed |
| increase weight beta of CVD loss (ablation) | CVD-GAN · image quality vs CVD metrics | FID and CVD metrics | Mixed |
| generate CVD-oriented images directly instead of StyleGAN plus recolor post-processing | CVD-GAN · Abstract Art, protan 100% | Perceptual loss: StyleGAN 1.0350 -> 0.6606; Huang recolor 0.5333 | Mixed |
| add CVD losses to StyleGAN | StyleGAN · Flowers | FID: 8.23 -> 18.93 | Hurt |
| add CVD losses to StyleGAN | StyleGAN · Abstract Art | FID: 14.35 -> 17.73 | Hurt |
| apply CVD-GAN at low severity | CVD-GAN · Flowers, protan 20% | Local contrast decay: 0.5937 -> 0.6829 | Hurt |
Closest papers by meaning
- EnColor: Improving Visual Accessibility with a Deep Encoder-Decoder Image Corrector for Color Vision Deficient Individuals (AAAI 2024 · similarity 0.86)
- PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation (CVPR 2025 · similarity 0.82)
- Image Generation Diversity Issues and How to Tame Them (CVPR 2025 · similarity 0.81)
- Personalized Representation from Personalized Generation (ICLR 2025 · similarity 0.81)
- Boost Your Human Image Generation Model via Direct Preference Optimization (CVPR 2025 · similarity 0.81)
- BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities (ICLR 2025 · similarity 0.80)
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.
