Research map / Image generation / Super-resolution
Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution
Jingkai Wang, Yixin Tang, Jue Gong, Jiatong Li, Shu Li, Libo Liu, Jianliang Lan, Yutong Liu, Yulun 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 |
|---|---|---|---|
| use CLIP-ConvNeXt discriminator with RaGAN instead of no GAN (ablation) | StrSR · DIV2K-val | MUSIQ: 54.086 -> 65.106 | Improved |
| use relativistic GAN loss instead of non-saturating GAN (ablation) | StrSR · DIV2K-val | MUSIQ: 61.820 -> 65.106 | Improved |
| add VLM-encoded semantic embeddings instead of naive text encoder (ablation) | StrSR · DIV2K-val | MUSIQ: 62.093 -> 65.106 | Improved |
| add VLM embeddings versus no embedding (ablation) | StrSR · DIV2K-val | MANIQA: 0.5043 -> 0.5754 | Improved |
| add frequency distribution loss (FDL) (ablation) | StrSR · DIV2K-val | grid-like artifacts (qualitative) | Improved |
| use StrSR one-step DiT distillation vs other one-step methods | StrSR-FLUX · DIV2K-val | LPIPS: 0.3551 -> 0.2992 (vs HYPIR) | Improved |
| StrSR versus baselines on pixel fidelity | StrSR-Z · DIV2K-val | PSNR: 23.24 -> 21.35 (vs SeeSR) | Hurt |
| use FLUX.2 klein base rather than Z-Image-Turbo | StrSR · RealSR | LPIPS: 0.3215 -> 0.2599 | 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.
- SeeSR — SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution (CVPR 2024) · better on 2 of 2 shared results
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
- Effective Diffusion Transformer Architecture for Image Super-Resolution (AAAI 2025 · similarity 0.91)
- One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation (ICML 2025 · similarity 0.89)
- Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator (NeurIPS 2025 · similarity 0.88)
- SinSR: Diffusion-Based Image Super-Resolution in a Single Step (CVPR 2024 · similarity 0.88)
- When Latents Forget Pixels: Restoring Fidelity in Diffusion Transformer Super-Resolution (NeurIPS 2026 · similarity 0.88)
- Adversarial Diffusion Compression 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.
