Research map / Image generation / Super-resolution
Super-Resolving Very Low-Resolution Face Images With Supplementary Attributes
Read the paperCheck 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 attribute-embedded upsampling instead of TDAE | Face super-resolution · CelebA test dataset | PSNR: 20.40 -> 21.82 | Helped |
| Use attribute-embedded upsampling instead of TDAE | Face super-resolution · CelebA test dataset | SSIM: 0.57 -> 0.62 | Helped |
| Increase the Young attribute | Attribute-embedded upsampling network · CelebA attribute: Young | true positive accuracy: 0% -> 100% | Helped |
| Increase the Male attribute | Attribute-embedded upsampling network · CelebA attribute: Male | true positive accuracy: 0% -> 100% | Helped |
| Increase the Big nose attribute | Attribute-embedded upsampling network · CelebA attribute: Big nose | true positive accuracy: 8.33% -> 100% | Helped |
| Add an autoencoder and embed attributes in residual features rather than directly concatenating attributes with the LR input (ablation) | Attribute-embedded upsampling network · Very-low-resolution face super-resolution | visual fidelity | Helped |
| Add skip connections to the autoencoder (ablation) | Attribute-embedded upsampling network · Very-low-resolution face super-resolution | visual fidelity | Helped |
| Add perceptual loss alongside pixel-wise ℓ2 loss (ablation) | Attribute-embedded upsampling network · Very-low-resolution face super-resolution | visual fidelity | Helped |
| Add losses beyond pixel-wise ℓ2 loss (ablation) | Attribute-embedded upsampling network · Very-low-resolution face super-resolution | visual fidelity | Helped |
| Add attribute embedding with a conditional discriminative network (ablation) | Attribute-embedded upsampling network · Very-low-resolution face super-resolution | attribute consistency | Helped |
Closest papers by meaning
- Hallucinating Very Low-Resolution Unaligned and Noisy Face Images by Transformative Discriminative Autoencoders (CVPR 2017 · similarity 0.91)
- Face Hallucination with Tiny Unaligned Images by Transformative Discriminative Neural Networks (AAAI 2017 · similarity 0.89)
- FSRNet: End-to-End Learning Face Super-Resolution With Facial Priors (CVPR 2018 · similarity 0.89)
- GCFSR: A Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors (CVPR 2022 · similarity 0.89)
- Residual Attribute Attention Network for Face Image Super-Resolution (AAAI 2019 · similarity 0.88)
- Low-Light Face Super-resolution via Illumination, Structure, and Texture Associated Representation (AAAI 2024 · similarity 0.88)
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.