Research map / Image generation / Super-resolution
Detail-Preserving Transformer for Light Field Image Super-resolution
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 DPT instead of LF-DFNet | LFSR · EPFL ×4 | PSNR: 28.77 -> 28.93 | Helped |
| Add the gradient Transformer to the content-only model (ablation) | DPT · EPFL ×4 | PSNR: 28.77 -> 28.86 | Helped |
| Add the gradient Transformer to the content-only model (ablation) | DPT · EPFL ×4 | SSIM: 0.9142 -> 0.9153 | Helped |
| Use cross-attention sequence fusion instead of sum fusion (ablation) | DPT · EPFL ×4 | PSNR: 28.86 -> 28.93 | Helped |
| Use cross-attention sequence fusion instead of image-level Transformer fusion (ablation) | DPT · EPFL ×4 | PSNR: 28.81 -> 28.93 | Helped |
| Use Transformer branches instead of residual-block branches (ablation) | DPT · EPFL ×4 | PSNR: 28.72 -> 28.93 | Helped |
| Use SA-LSA instead of vanilla fully-connected self-attention (ablation) | DPT · EPFL ×4 | PSNR: 28.89 -> 28.93 | Helped |
| Set attention-block count K to 2 rather than 1 (ablation) | DPT · EPFL ×4 | PSNR: 28.69 -> 28.93 | Helped |
| Set attention-block count K to 2 rather than 3 (ablation) | DPT · EPFL ×4 | PSNR: 28.78 -> 28.93 | Helped |
| Set attention-block count K to 2 rather than 4 (ablation) | DPT · EPFL ×4 | PSNR: 28.74 -> 28.93 | Helped |
Closest papers by meaning
- Recursive Generalization Transformer for Image Super-Resolution (ICLR 2024 · similarity 0.88)
- Occlusion-Embedded Hybrid Transformer for Light Field Super-Resolution (AAAI 2025 · similarity 0.87)
- Progressive Focused Transformer for Single Image Super-Resolution (CVPR 2025 · similarity 0.86)
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning (CVPR 2024 · similarity 0.86)
- NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis (CVPR 2024 · similarity 0.86)
- When Latents Forget Pixels: Restoring Fidelity in Diffusion Transformer Super-Resolution (NeurIPS 2026 · 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.