Research map / Image generation / Autoregressive and latent generation
HiEI: A Universal Framework for Generating High-quality Emerging Images from Natural Images
Jingmeng Li, Lukang Fu, Surun Yang, Hui Wei
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 |
|---|---|---|---|
| replace OcTree color quantization with TTNet (ablation) | HiEI · Animal 2K test | content loss: 1.32 -> 0.98 | Improved |
| replace ColorCNN color quantization with TTNet (ablation) | HiEI · Animal 2K test | content loss: 1.21 -> 0.98 | Improved |
| use HiEI instead of binarized universal style transfer models | EI generation · Binarized EI comparison | style loss: 0.28 -> 0.19 | Improved |
| swap rendering template from T+ to T- (invert foreground and background colors) (ablation) | HiEI · Binarized EI comparison | content loss: 1.02 -> 1.05 | Hurt |
| fine-tune YOLOv8 on emerging-image data instead of natural images | YOLOv8 · PASCALEI testvalEI | success rate: 0.103 -> 0.291 | Improved |
| convert natural images to emerging images before classification | ResNet34 · STL-10 | top-1 accuracy: 0.878 -> 0.265 | Hurt |
| convert natural images to emerging images before object detection | YOLOv8 · PASCAL VOC2012 | success rate: 0.709 -> 0.103 | Hurt |
| HiEI emerging images for humans versus deep model | human observers · PASCALEI testvalEI | success rate: 1 -> 0.89 | No clear effect |
Closest papers by meaning
- MI-CAPTCHA: Enhance the Security of CAPTCHA Using Mooney Images (AAAI 2025 · similarity 0.84)
- Are High-Quality AI-Generated Images More Difficult for Models to Detect? (ICML 2025 · similarity 0.84)
- EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models (CVPR 2024 · similarity 0.83)
- ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis (NeurIPS 2024 · similarity 0.83)
- Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection (NeurIPS 2025 · similarity 0.83)
- Devil is in the Detail: Towards Injecting Fine Details of Image Prompt in Image Generation via Conflict-free Guidance and Stratified Attention (CVPR 2025 · 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.
