Research map / Image generation / Super-resolution
LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation
Ruizhi Shao, Gaochang Wu, Yuemei Zhou, Ying Fu, Lu Fang, Yebin Liu
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 |
|---|---|---|---|
| replace feature-based/deep baselines with LocalTrans local transformer | cross-resolution homography estimation · MS-COCO 4x gap | PSNR: 27.89 -> 30.17 | Improved |
| replace MHN with LocalTrans | cross-resolution homography estimation · MS-COCO 8x gap | PSNR: 20.24 -> 24.12 | Improved |
| replace MHN with LocalTrans | cross-resolution homography estimation · MS-COCO 8x gap | SSIM: 0.860 -> 0.930 | Improved |
| use local attention kernel instead of global attention (1 scale) (ablation) | multiscale transformer · 128x128 input, 1 scale | speed: 152fps -> 249fps | Improved |
| use local attention kernel instead of global attention (3 scales) (ablation) | multiscale transformer · 128x128 input, 3 scales | speed: 16.4fps -> 132fps | Improved |
| use local attention kernel instead of global attention (3 scales) (ablation) | multiscale transformer · 128x128 input, 3 scales | GPU memory: 476.9M -> 67.7M | Improved |
| use local attention kernel instead of global attention (3 scales) (ablation) | multiscale transformer · 256x256 input, 3 scales | speed: 4.31fps -> 87.7fps | Improved |
| use local attention kernel instead of global attention (3 scales) (ablation) | multiscale transformer · 256x256 input, 3 scales | GPU memory: 2434M -> 287.0M | Improved |
| use local attention kernel instead of global attention (1 scale) (ablation) | multiscale transformer · 256x256 input, 1 scale | GPU memory: 208.4M -> 196.9M | No clear effect |
| use multiscale local transformer instead of single-scale global transformer (ablation) | LocalTrans · cross-resolution homography | accuracy | Improved |
Closest papers by meaning
- MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography Estimation (CVPR 2024 · similarity 0.88)
- SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split Optimization (CVPR 2025 · similarity 0.88)
- Adapting Dense Matching for Homography Estimation with Grid-based Acceleration (CVPR 2025 · similarity 0.87)
- ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses (NeurIPS 2024 · similarity 0.86)
- Deep Homography Estimation for Visual Place Recognition (AAAI 2024 · similarity 0.86)
- Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization (NeurIPS 2024 · similarity 0.84)
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.
