Spline refinement with differentiable rendering
This method enhances spline refinement for computational microscopy, particularly in biomedical research like drug discovery, but appears incremental as it builds on existing coordinate- and pixel-based approaches.
The paper tackled the challenge of detecting slender, overlapping structures in computational microscopy by introducing a training-free differentiable rendering approach for spline refinement, achieving sub-pixel accuracy and improving spline quality on C. elegans nematodes.
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.