# Learning and Segmenting Dense Voxel Embeddings for 3D Neuron Reconstruction

arXiv: https://arxiv.org/abs/1909.09872 · HTML: https://mlsanity.com/paper/1909.09872/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2019.

## Built on by (most cited first, 8 of 8)

- [Sparse Object-level Supervision for Instance Segmentation with Pixel Embeddings](https://mlsanity.com/paper/2103.14572/) (2021)
- [Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing](https://mlsanity.com/paper/2401.03043/) (2024)
- [FISBe: A real-world benchmark dataset for instance segmentation of long-range thin filamentous structures](https://mlsanity.com/paper/2404.00130/) (2024)
- [Biomedical Image Segmentation: A Systematic Literature Review of Deep Learning Based Object Detection Methods](https://mlsanity.com/paper/2408.03393/) (2024)
- [A Graph Multi-separator Problem for Image Segmentation](https://mlsanity.com/paper/2307.04592/) (2023)
- [Graph Relation Distillation for Efficient Biomedical Instance Segmentation](https://mlsanity.com/paper/2401.06370/) (2024)
- [NeuroMamba: Multi-Perspective Feature Interaction with Visual Mamba for Neuron Segmentation](https://mlsanity.com/paper/2601.15929/) (2026)
- [μMatch: Foundation Models for Semi-supervised Learning and Domain Adaptation in EM](https://mlsanity.com/paper/2606.21605/) (2026)

## Abstract (arXiv)

We show dense voxel embeddings learned via deep metric learning can be employed to produce a highly accurate segmentation of neurons from 3D electron microscopy images. A "metric graph" on a set of edges between voxels is constructed from the dense voxel embeddings generated by a convolutional network. Partitioning the metric graph with long-range edges as repulsive constraints yields an initial segmentation with high precision, with substantial accuracy gain for very thin objects. The convolutional embedding net is reused without any modification to agglomerate the systematic splits caused by complex "self-contact" motifs. Our proposed method achieves state-of-the-art accuracy on the challenging problem of 3D neuron reconstruction from the brain images acquired by serial section electron microscopy. Our alternative, object-centered representation could be more generally useful for other computational tasks in automated neural circuit reconstruction.