# Voxel-wise Cross-Volume Representation Learning for 3D Neuron Reconstruction

arXiv: https://arxiv.org/abs/2108.06522 · HTML: https://mlsanity.com/paper/2108.06522/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 14 Aug 2021.

## Builds on (most cited first, 14 of 14)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation](https://mlsanity.com/paper/1707.03718/) (2017)
- [Can Semantic Labels Assist Self-Supervised Visual Representation Learning?](https://mlsanity.com/paper/2011.08621/) (2020)
- [Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning](https://mlsanity.com/paper/2101.07525/) (2021)
- [Single Neuron Segmentation using Graph-based Global Reasoning with Auxiliary Skeleton Loss from 3D Optical Microscope Images](https://mlsanity.com/paper/2101.08910/) (2021)
- [3D Reconstruction and Segmentation of Dissection Photographs for MRI-free Neuropathology](https://mlsanity.com/paper/2009.05596/) (2020)

## Built on by (most cited first, 4 of 4)

- [PointNeuron: 3D Neuron Reconstruction via Geometry and Topology Learning of Point Clouds](https://mlsanity.com/paper/2210.08305/) (2022)
- [Boosting 3D Neuron Segmentation with 2D Vision Transformer Pre-trained on Natural Images](https://mlsanity.com/paper/2405.02686/) (2024)
- [NeuroSeg Meets DINOv3: Transferring 2D Self-Supervised Visual Priors to 3D Neuron Segmentation via DINOv3 Initialization](https://mlsanity.com/paper/2603.23104/) (2026)
- [DINeuro: Distilling Knowledge from 2D Natural Images via Deformable Tubular Transferring Strategy for 3D Neuron Reconstruction](https://mlsanity.com/paper/2410.22078/) (2024)

## Abstract (arXiv)

Automatic 3D neuron reconstruction is critical for analysing the morphology and functionality of neurons in brain circuit activities. However, the performance of existing tracing algorithms is hinged by the low image quality. Recently, a series of deep learning based segmentation methods have been proposed to improve the quality of raw 3D optical image stacks by removing noises and restoring neuronal structures from low-contrast background. Due to the variety of neuron morphology and the lack of large neuron datasets, most of current neuron segmentation models rely on introducing complex and specially-designed submodules to a base architecture with the aim of encoding better feature representations. Though successful, extra burden would be put on computation during inference. Therefore, rather than modifying the base network, we shift our focus to the dataset itself. The encoder-decoder backbone used in most neuron segmentation models attends only intra-volume voxel points to learn structural features of neurons but neglect the shared intrinsic semantic features of voxels belonging to the same category among different volumes, which is also important for expressive representation learning. Hence, to better utilise the scarce dataset, we propose to explicitly exploit such intrinsic features of voxels through a novel voxel-level cross-volume representation learning paradigm on the basis of an encoder-decoder segmentation model. Our method introduces no extra cost during inference. Evaluated on 42 3D neuron images from BigNeuron project, our proposed method is demonstrated to improve the learning ability of the original segmentation model and further enhancing the reconstruction performance.