Research map / Image generation / Super-resolution
Zero-Shot Image Super-Resolution with Depth Guided Internal Degradation Learning
Xi Cheng, Zhenyong Fu, Jian Yang
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 |
|---|---|---|---|
| add depth guided patch selection (ablation) | DGDML-SR without bi-cycle training · NYU | NIQE: 5.929 -> 5.809 | Improved |
| add bi-cycle training (ablation) | DGDML-SR without depth guidance · NYU | NIQE: 5.929 -> 5.499 | Improved |
| add depth guidance on top of bi-cycle training (ablation) | DGDML-SR with BCN · NYU | NIQE: 5.499 -> 4.824 | Improved |
| add depth guided patch selection (ablation) | DGDML-SR without bi-cycle training · B3DO | NIQE: 5.193 -> 4.676 | Improved |
| add bi-cycle training (ablation) | DGDML-SR without depth guidance · B3DO | NIQE: 5.193 -> 4.328 | Improved |
| add depth guidance on top of bi-cycle training (ablation) | DGDML-SR with BCN · B3DO | NIQE: 4.328 -> 4.281 | Improved |
| add depth guided patch selection (ablation) | DGDML-SR without bi-cycle training · SUN RGBD | NIQE: 4.926 -> 4.687 | Improved |
| add bi-cycle training (ablation) | DGDML-SR without depth guidance · SUN RGBD | NIQE: 4.926 -> 4.253 | Improved |
| add depth guidance on top of bi-cycle training (ablation) | DGDML-SR with BCN · SUN RGBD | NIQE: 4.253 -> 4.008 | Improved |
| learned degradation (DGDML-SR) instead of bicubic-kernel ZSSR | zero-shot SR · NYU x2 | NIQE: 5.753 -> 4.824 | Improved |
| learned degradation instead of KernelGAN kernel | zero-shot SR · B3DO x2 | NIQE: 6.859 -> 4.281 | Improved |
| use zero-shot DGDML-SR instead of supervised RCAN | SR · SUN RGBD x4 | NIQE: 6.458 -> 5.473 | Improved |
Closest papers by meaning
- Learning a Single Convolutional Super-Resolution Network for Multiple Degradations (CVPR 2018 · similarity 0.91)
- “Zero-Shot” Super-Resolution Using Deep Internal Learning (CVPR 2018 · similarity 0.91)
- Deep Plug-And-Play Super-Resolution for Arbitrary Blur Kernels (CVPR 2019 · similarity 0.90)
- Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution (ECCV 2022 · similarity 0.90)
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning (CVPR 2024 · similarity 0.89)
- DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution (CVPR 2025 · similarity 0.89)
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.
