Research map / 3D vision / 3D generation
Large-Scale Multi-Hypotheses Cell Tracking Using Ultrametric Contours Maps
Jordão Bragantini, Merlin Lange, Loïc A Royer
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 |
|---|---|---|---|
| ensemble Watershed, Cellpose and Stardist segmentations via fuzzy contour maps (ablation) | ultrametric-contour-map cell tracking ILP · Fluo-N2DL-HeLa file 1 | CTB: 0.817 -> 0.848 | Improved |
| ensemble Watershed, Cellpose and Stardist segmentations (ablation) | ultrametric-contour-map cell tracking ILP · Fluo-N2DL-HeLa file 2 | CTB: 0.880 -> 0.891 | Improved |
| use the paper's ILP formulation for division and field-of-view constraints instead of prior ILP formulations (ablation) | cell tracking ILP · Fluo-N3DH-CE run time | run time slope coefficient: 1.75 -> 1.37 | Improved |
| use image processing (IM) segmentation instead of pseudo-label-trained U-Net (ablation) | tracking on DRO, TRIF, TRIC · Cell Tracking Challenge | tracking accuracy | Improved |
| use the method on MDA231 with its learned edge network | tracking on MDA231 · Cell Tracking Challenge MDA231 | CTB: 0.683 vs 0.797 best | Hurt |
| use MALA boundary predictions instead of Gaussian-filtered images as contour map (ablation) | tracking on Epithelial Cell Benchmark · Epithelial Cell Benchmark PER | SEG: 0.853 -> 0.909 | Improved |
| apply the method to TRIC dataset where cell motion is inflated at the periphery | tracking on TRIC · Cell Tracking Challenge TRIC | CTB: 0.754 vs 0.867 best | Hurt |
Closest papers by meaning
- Trackastra: Transformer-based cell tracking for live-cell microscopy (ECCV 2024 · similarity 0.90)
- Higher-Order Cell Tracking Transformer (NeurIPS 2026 · similarity 0.87)
- ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy (ICML 2025 · similarity 0.84)
- Towards Scalable Context-Aware Single-Cell Spatial Transcriptomics Prediction from Histology Images (NeurIPS 2026 · similarity 0.84)
- Cross-Dimension Affinity Distillation for 3D EM Neuron Segmentation (CVPR 2024 · similarity 0.83)
- Bridging Protein Sequences and Microscopy Images with Unified Diffusion Models (ICML 2025 · similarity 0.83)
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.
