Research map / Learning theory and algorithms / Combinatorial and search optimization
OATM: Occlusion Aware Template Matching by Consensus Set Maximization
Simon Korman, Mark Milam, Stefano Soatto
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 OATM's explicit search over affine deformations and occlusion-aware consensus matching instead of descriptor-based matching | Template matching on HPatches · HPatches, Hard and Tough cases | mAP | Improved |
| Use OATM instead of Fast-Match | Affine template matching · Synthetic occlusion experiment | center location error | Improved |
| Use OATM instead of Fast-Match | Affine template matching · Synthetic occlusion experiment, inlier rates under 0.75 | center location error | Improved |
| Use OATM instead of DDIS | Template matching with occlusion · Synthetic occlusion experiment | center location error | Improved |
| Use OATM's adaptive stopping criterion | OATM · Synthetic occlusion experiment | runtime | Hurt |
| Reduce the search to two approximately equal-sized sets and search their product via random grid hashing | OATM · 2D-affine scalability experiment | runtime scaling | Improved |
Closest papers by meaning
- Best-Buddies Similarity—Robust Template Matching Using Mutual Nearest Neighbors (TPAMI 2017 · similarity 0.88)
- Efficient Sliding Window Computation for NN-Based Template Matching (ECCV 2018 · similarity 0.85)
- Occ^2Net: Robust Image Matching Based on 3D Occupancy Estimation for Occluded Regions (ICCV 2023 · similarity 0.85)
- HiPPI: Higher-Order Projected Power Iterations for Scalable Multi-Matching (ICCV 2019 · similarity 0.85)
- QATM: Quality-Aware Template Matching for Deep Learning (CVPR 2019 · similarity 0.85)
- Model-free Consensus Maximization for Non-Rigid Shapes (ECCV 2018 · 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.
