Research map / Image generation / Autoregressive and latent generation
Efficient Sliding Window Computation for NN-Based Template Matching
Lior Talker, Yael Moses, Ilan Shimshoni
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 window-based popularity with image-based popularity (DIS to IWU) | DIS · BBS (RGB) | runtime (s): 0.020 -> 0.009 | Improved |
| replace DDIS with DIWU (L1 misalignment, image-based popularity, incremental sliding window) | DDIS · BBS (RGB) | runtime (s): 1.030 -> 0.024 | Improved |
| replace DDIS with DIWU | DDIS · TinyTLP (RGB) | runtime (s): 42.3 -> 0.209 | Improved |
| replace DIS with IWU | DIS · TinyTLP (RGB) | runtime (s): 0.391 -> 0.059 | Improved |
| replace DIS with IWU | DIS · BBS (RGB) | success rate: 0.565 -> 0.624 | Improved |
| replace DIS with IWU | DIS · BBS (VGG) | success rate: 0.661 -> 0.662 | No clear effect |
| add deformation (misalignment) score to IWU (IWU to DIWU) (ablation) | IWU · BBS (RGB) | success rate: 0.624 -> 0.708 | Improved |
| add deformation (misalignment) score to IWU (IWU to DIWU) (ablation) | IWU · TinyTLP (RGB) | success rate: 0.553 -> 0.681 | Improved |
| replace DDIS with DIWU | DDIS · BBS (RGB) | success rate: 0.697 -> 0.708 | No clear effect |
| replace DDIS with DIWU | DDIS · BBS (VGG) | success rate: 0.724 -> 0.721 | No clear effect |
| replace DDIS with DIWU | DDIS · TinyTLP (RGB) | success rate: 0.629 -> 0.681 | Improved |
| replace DDIS with DIWU | DDIS · TinyTLP (VGG) | mean IoU: 0.562 -> 0.590 | Improved |
Closest papers by meaning
- Template Matching With Deformable Diversity Similarity (CVPR 2017 · similarity 0.86)
- FastJAM: a Fast Joint Alignment Model for Images (NeurIPS 2025 · similarity 0.82)
- HomoMatcher: Achieving Dense Feature Matching with Semi-Dense Efficiency by Homography Estimation (AAAI 2025 · similarity 0.81)
- XFeat: Accelerated Features for Lightweight Image Matching (CVPR 2024 · similarity 0.81)
- GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 · similarity 0.81)
- RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges (CVPR 2025 · similarity 0.81)
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.
