Research map / Image generation / Super-resolution
GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution
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 a pre-trained GAN as a latent bank in an encoder-bank-decoder SR network | GLEAN · CelebA-HQ, 16× SR | ArcFace cosine similarity: 0.9599 -> 0.9678 | Helped |
| Use a pre-trained GAN as a latent bank in an encoder-bank-decoder SR network | GLEAN · Face, 16× SR | PSNR: 26.76 -> 26.84 | Helped |
| Use a pre-trained GAN as a latent bank in an encoder-bank-decoder SR network | GLEAN · Cat, 16× SR | PSNR: 19.99 -> 20.92 | Helped |
| Use a pre-trained GAN as a latent bank in an encoder-bank-decoder SR network | GLEAN · Bedroom, 16× SR | PSNR: 19.47 -> 19.44 | Hurt |
| Use multi-resolution encoder features to condition the latent bank (ablation) | GLEAN · Large-factor image SR | local structure and detail fidelity | Helped |
| Use multi-resolution encoder features to condition the latent bank (ablation) | GLEAN · Large-factor image SR | local structure and detail fidelity | Hurt |
| Pass latent-bank features to the decoder (ablation) | GLEAN · Large-factor image SR | structure and texture quality | Helped |
| Add the decoder to aggregate encoder and bank features coarse-to-fine (ablation) | GLEAN · Large-factor image SR | visual detail quality | Helped |
| Keep the pre-trained latent bank fixed during training (ablation) | GLEAN · Large-factor image SR | restoration quality | No clear effect |
| Use a different latent vector for each generator block (ablation) | GLEAN · Large-factor image SR | artifact frequency | Helped |
Closest papers by meaning
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (CVPR 2017 · similarity 0.90)
- GSDD: Generative Space Dataset Distillation for Image Super-resolution (AAAI 2024 · similarity 0.89)
- StyleSwin: Transformer-Based GAN for High-Resolution Image Generation (CVPR 2022 · similarity 0.88)
- Uncertainty-Aware GAN for Single Image Super Resolution (AAAI 2024 · similarity 0.88)
- SeD: Semantic-Aware Discriminator for Image Super-Resolution (CVPR 2024 · similarity 0.87)
- Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts (CVPR 2024 · 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.