Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.14525 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918154204086272 |
|---|---|
| author | Zdyb, Frans Alonso, Albert Kirkegaard, Julius B. |
| author_facet | Zdyb, Frans Alonso, Albert Kirkegaard, Julius B. |
| contents | Detecting slender, overlapping structures remains a challenge in computational microscopy. While recent coordinate-based approaches improve detection, they often produce less accurate splines than pixel-based methods. We introduce a training-free differentiable rendering approach to spline refinement, achieving both high reliability and sub-pixel accuracy. Our method improves spline quality, enhances robustness to distribution shifts, and shrinks the gap between synthetic and real-world data. Being fully unsupervised, the method is a drop-in replacement for the popular active contour model for spline refinement. Evaluated on C. elegans nematodes, a popular model organism for drug discovery and biomedical research, we demonstrate that our approach combines the strengths of both coordinate- and pixel-based methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_14525 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Spline refinement with differentiable rendering Zdyb, Frans Alonso, Albert Kirkegaard, Julius B. Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Applications Detecting slender, overlapping structures remains a challenge in computational microscopy. While recent coordinate-based approaches improve detection, they often produce less accurate splines than pixel-based methods. We introduce a training-free differentiable rendering approach to spline refinement, achieving both high reliability and sub-pixel accuracy. Our method improves spline quality, enhances robustness to distribution shifts, and shrinks the gap between synthetic and real-world data. Being fully unsupervised, the method is a drop-in replacement for the popular active contour model for spline refinement. Evaluated on C. elegans nematodes, a popular model organism for drug discovery and biomedical research, we demonstrate that our approach combines the strengths of both coordinate- and pixel-based methods. |
| title | Spline refinement with differentiable rendering |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Applications |
| url | https://arxiv.org/abs/2503.14525 |