Research map / Image generation / Super-resolution
Face Hallucination with Tiny Unaligned Images by Transformative Discriminative Neural Networks
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 |
|---|---|---|---|
| TDN (multi-STN upsampling + discriminator) vs prior methods with STN0 alignment | face hallucination · CelebA 8x | PSNR: 4.25 dB | Helped |
| add discriminative network to upsampling network (ablation) | TDN · CelebA 8x | PSNR: 0.18 dB | Hurt |
| apply multiple STNs on feature maps instead of a single STN on the LR image (ablation) | TDN · CelebA 8x | visual alignment quality | Helped |
Closest papers by meaning
- Analyzing and Mitigating Object Hallucination: A Training Bias Perspective (AAAI 2026 · similarity 0.84)
- Hallucination-aware Intermediate Representation Editing in Large Vision-Lanugage Models (ICLR 2026 · similarity 0.84)
- Image Token Matters: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing (NeurIPS 2025 · similarity 0.84)
- Reducing Hallucinations in Large Vision-Language Models via Latent Space Steering (ICLR 2025 · similarity 0.84)
- HulluEdit: Single-Pass Evidence-Consistent Subspace Editing for Mitigating Hallucinations in Large Vision-Language Models (CVPR 2026 · similarity 0.84)
- Mitigating Object Hallucination in Large Vision-Language Models via False Discovery Controlled Visual Data Splitting (NeurIPS 2026 · 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.