Research map / Image generation / Super-resolution
Joint Geometric and Trajectory Consistency Learning for One-Step Real-World Super-Resolution
Chengyan Deng, Zhangquan Chen, Li Yu, Kai Zhang, Xue Zhou, Wang Zhang
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 trajectory alignment loss L_TA in Stage I (ablation) | GTASR Stage I · ImageNet-Test | PSNR: 24.65 -> 25.05 | Improved |
| add trajectory alignment loss L_TA in Stage I (ablation) | GTASR Stage I · ImageNet-Test | LPIPS: 0.2073 -> 0.1856 | Improved |
| add trajectory alignment loss L_TA in Stage I (ablation) | GTASR Stage I · ImageNet-Test | MANIQA: 0.3830 -> 0.4457 | Improved |
| add L_Stab to DTM in Stage II (ablation) | GTASR Stage II · ImageNet-Test | MANIQA: 0.5070 -> 0.5676 | Improved |
| add L_Stab to DTM in Stage II (ablation) | GTASR Stage II · ImageNet-Test | TOPIQ: 0.6863 -> 0.7349 | Improved |
| add L_Stab to DTM in Stage II (ablation) | GTASR Stage II · ImageNet-Test | PSNR: 24.76 -> 24.00 | Hurt |
| add L_Rect to DTM in Stage II (ablation) | GTASR Stage II · ImageNet-Test | MANIQA: 0.5070 -> 0.5403 | Improved |
| add L_Rect to DTM and L_Stab in Stage II (ablation) | GTASR Stage II · ImageNet-Test | MANIQA: 0.5676 -> 0.5826 | Improved |
| add L_Rect to DTM and L_Stab in Stage II (ablation) | GTASR Stage II · ImageNet-Test | PSNR: 24.00 -> 24.01 | No clear effect |
| use GTASR one-step instead of CTMSR-1 | CTMSR-1 · ImageNet-Test | MANIQA: 0.4857 -> 0.5826 | Improved |
| use GTASR one-step instead of CTMSR-1 | CTMSR-1 · ImageNet-Test | PSNR: 24.73 -> 24.01 | Hurt |
| use GTASR one-step instead of ResShift-15 | ResShift-15 · ImageNet-Test | runtime (s): 0.93 -> 0.08 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ResShift-15 — ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.88)
- SinSR: Diffusion-Based Image Super-Resolution in a Single Step (CVPR 2024 · similarity 0.88)
- NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution (NeurIPS 2026 · similarity 0.88)
- One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution (NeurIPS 2025 · similarity 0.87)
- StructSR: Refuse Spurious Details in Real-World Image Super-Resolution (AAAI 2025 · similarity 0.87)
- TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution (CVPR 2025 · similarity 0.87)
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.
