Research map / Detection and segmentation / CNN features
Tensorial template matching for fast cross-correlation with rotations and its application for tomography
Antonio Martinez-Sanchez, Ulrike Homberg, J. M. Almira, Harold Phelippeau
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 position refinement (TTM-ref) to TTM (ablation) | TTM · Synthetic L-shape tomogram | rotation error mean (degrees): 31.40 -> 0.03 | Improved |
| add position refinement (TTM-ref) to TTM (ablation) | TTM · Synthetic cylinder tomogram | position error mean (voxels): 2.38 -> 0.0 | Improved |
| add position refinement (TTM-ref) to TTM (ablation) | TTM · Synthetic 4CR2 tomogram | rotation error mean (degrees): 0.97 -> 0.11 | Improved |
| replace sampled-rotation template matching (PyTOM) with TTM | Synthetic tomograms, rotation accuracy · Synthetic 5MRC | rotation error mean (degrees): 3.02 -> 0.07 | Improved |
| replace PyTOM with TTM-ref for ribosome detection | EMPIAR-10988 best tomogram · EMPIAR-10988 | F1-score: 0.82 -> 0.85 | Improved |
| replace PyTOM with TTM-ref for ribosome detection on worst tomogram | EMPIAR-10988 worst tomogram · EMPIAR-10988 | F1-score: 0.67 -> 0.67 | No clear effect |
| TTM versus PyTOM under increased noise | TTM · Synthetic 4CR2 with noise | rotation deviation | Mixed |
| replace GPU template matching with CPU TTM | processing one tomogram · EMPIAR-10988 tomogram 960x928x230 | running time: several hours -> less than four minutes | Improved |
| TTM versus PyTOM on a symmetric template | TTM · Synthetic 3J9I and 3CF3 | rotation error mean (degrees): 2.48 -> 0.03 | Improved |
Closest papers by meaning
- Template Matching via Densities on the Roto-Translation Group (TPAMI 2017 · similarity 0.88)
- Efficient Sliding Window Computation for NN-Based Template Matching (ECCV 2018 · similarity 0.84)
- Template Matching With Deformable Diversity Similarity (CVPR 2017 · similarity 0.83)
- Low-Rank Tensor Completion: A Pseudo-Bayesian Learning Approach (ICCV 2017 · similarity 0.83)
- Coupled Laplacian Eigenmaps for Locally-Aware 3D Rigid Point Cloud Matching (CVPR 2024 · similarity 0.82)
- Tensor-Based Synchronization and the Low-Rankness of the Block Trifocal Tensor (NeurIPS 2024 · similarity 0.82)
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.
