# Spline refinement with differentiable rendering

arXiv: https://arxiv.org/abs/2503.14525 · HTML: https://mlsanity.com/paper/2503.14525/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 29 references that are in the map.
- First posted on arXiv 15 Mar 2025.

## Builds on (most cited first, 3 of 3)

- [Deep Learning Parametrization for B-Spline Curve Approximation](https://mlsanity.com/paper/1807.08304/) (2018)
- [Fast spline detection in high density microscopy data](https://mlsanity.com/paper/2301.04460/) (2023)
- [B-Spine: Learning B-Spline Curve Representation for Robust and Interpretable Spinal Curvature Estimation](https://mlsanity.com/paper/2310.09603/) (2023)

## Built on by (most cited first, 2 of 2)

- [rNCA: Self-Repairing Segmentation Masks](https://mlsanity.com/paper/2512.13397/) (2025)
- [Extremal Contours: Gradient-driven contours for compact visual attribution](https://mlsanity.com/paper/2511.01411/) (2025)

## Abstract (arXiv)

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.