Research map / Image generation / Super-resolution
Texture Vector-Quantization and Reconstruction Aware Prediction for Generative Super-Resolution
Qifan Li, Jiale Zou, Jinhua Zhang, Wei Long, Xingyu Zhou, Shuhang Gu
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 image-level reconstruction-aware supervision after code-level training (ablation) | TVQ&RAP · ImageNet-Test | FID: 32.876 -> 26.567 | Improved |
| Add image-level supervision (ablation) | TVQ&RAP · ImageNet-Test | index accuracy: 6.8% -> 4.4% | Hurt |
| Add image-level supervision (ablation) | TVQ&RAP · ImageNet-Test | MUSIQ: 61.687 -> 63.873 | Improved |
| Use texture vector quantization vs vanilla VQ codebook (ablation) | lightweight variant · ImageNet-Test | reconstruction/SR quality | Improved |
| Use 32x structure downsampling instead of 8x (ablation) | structure branch · ImageNet-Test | FID: 72.57 -> 33.23 | Improved |
| Use 32x structure downsampling instead of 128x (ablation) | structure branch · ImageNet-Test | FID: 35.00 -> 33.23 | Improved |
| Use 8x structure downsampling (ablation) | structure branch · ImageNet-Test | reconstruction PSNR: 25.26 -> 33.43 | Improved |
| Use TVQ latent instead of vanilla VQ latent (ablation) | codebook · K-means distortion K=512 | distortion: 9.55 -> 6.08 | Improved |
| Use TVQ&RAP instead of ResShift-15 | generative SR · ImageNet-Test | FID: 19.53 -> 26.57 | Hurt |
| Use TVQ&RAP instead of ResShift-15 | generative SR · runtime | runtime: 689ms -> 38ms | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SinSR-1 — SinSR: Diffusion-Based Image Super-Resolution in a Single Step (CVPR 2024) · better on 6 of 7 shared results
- ResShift-15 — ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS 2023) · better on 4 of 6 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
- Visual Autoregressive Modeling for Image Super-Resolution (ICML 2025 · similarity 0.87)
- Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts (CVPR 2024 · similarity 0.86)
- Boosting Flow-based Generative Super-Resolution Models via Learned Prior (CVPR 2024 · similarity 0.86)
- HyperVQ: Enabling Hyperprior Entropy Modeling for VQ-Based Generative Image Compression (NeurIPS 2026 · similarity 0.86)
- SeD: Semantic-Aware Discriminator for Image Super-Resolution (CVPR 2024 · similarity 0.86)
- PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors (NeurIPS 2025 · 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.
