# Superpixel Segmentation with Fully Convolutional Networks

arXiv: https://arxiv.org/abs/2003.12929 · HTML: https://mlsanity.com/paper/2003.12929/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2020.

## Built on by (most cited first, 30 of 72)

- [Accurate and Efficient Stereo Matching via Attention Concatenation Volume](https://mlsanity.com/paper/2209.12699/) (2022)
- [Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation](https://mlsanity.com/paper/2108.05773/) (2021)
- [Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction](https://mlsanity.com/paper/2406.03697/) (2024)
- [Vision Transformer with Super Token Sampling](https://mlsanity.com/paper/2211.11167/) (2022)
- [Image as Set of Points](https://mlsanity.com/paper/2303.01494/) (2023)
- [CLUSTSEG: Clustering for Universal Segmentation](https://mlsanity.com/paper/2305.02187/) (2023)
- [HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2305.13031/) (2023)
- [Unsupervised Video Object Segmentation via Prototype Memory Network](https://mlsanity.com/paper/2209.03712/) (2022)
- [Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata](https://mlsanity.com/paper/2206.01813/) (2022)
- [Self-Conditioned Probabilistic Learning of Video Rescaling](https://mlsanity.com/paper/2107.11639/) (2021)
- [Raw Image Reconstruction with Learned Compact Metadata](https://mlsanity.com/paper/2302.12995/) (2023)
- [Learning-based Multi-View Stereo: A Survey](https://mlsanity.com/paper/2408.15235/) (2024)
- [CGI-Stereo: Accurate and Real-Time Stereo Matching via Context and Geometry Interaction](https://mlsanity.com/paper/2301.02789/) (2023)
- [Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial Regularization](https://mlsanity.com/paper/2107.00691/) (2021)
- [SPFormer: Enhancing Vision Transformer with Superpixel Representation](https://mlsanity.com/paper/2401.02931/) (2024)
- [Learning the Superpixel in a Non-iterative and Lifelong Manner](https://mlsanity.com/paper/2103.10681/) (2021)
- [Beyond Learned Metadata-based Raw Image Reconstruction](https://mlsanity.com/paper/2306.12058/) (2023)
- [Dual-stage Hyperspectral Image Classification Model with Spectral Supertoken](https://mlsanity.com/paper/2407.07307/) (2024)
- [HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation](https://mlsanity.com/paper/2106.03755/) (2021)
- [Less is More: Unsupervised Mask-guided Annotated CT Image Synthesis with Minimum Manual Segmentations](https://mlsanity.com/paper/2303.12747/) (2023)
- [A comprehensive review and new taxonomy on superpixel segmentation](https://mlsanity.com/paper/2409.19179/) (2024)
- [Survey of Image Based Graph Neural Networks](https://mlsanity.com/paper/2106.06307/) (2021)
- [Superevents: Towards Native Semantic Segmentation for Event-based Cameras](https://mlsanity.com/paper/2105.06091/) (2021)
- [SoftPool++: An Encoder-Decoder Network for Point Cloud Completion](https://mlsanity.com/paper/2205.03899/) (2022)
- [Learning Invariant Inter-pixel Correlations for Superpixel Generation](https://mlsanity.com/paper/2402.18201/) (2024)
- [Compositional Neural Textures](https://mlsanity.com/paper/2404.12509/) (2024)
- [Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift](https://mlsanity.com/paper/2103.14417/) (2021)
- [Efficient Multiscale Object-based Superpixel Framework](https://mlsanity.com/paper/2204.03533/) (2022)
- [Improving Scene Graph Generation with Superpixel-Based Interaction Learning](https://mlsanity.com/paper/2308.02339/) (2023)
- [Homeomorphism Prior for False Positive and Negative Problem in Medical Image Dense Contrastive Representation Learning](https://mlsanity.com/paper/2502.05282/) (2025)

## Abstract (arXiv)

In computer vision, superpixels have been widely used as an effective way to reduce the number of image primitives for subsequent processing. But only a few attempts have been made to incorporate them into deep neural networks. One main reason is that the standard convolution operation is defined on regular grids and becomes inefficient when applied to superpixels. Inspired by an initialization strategy commonly adopted by traditional superpixel algorithms, we present a novel method that employs a simple fully convolutional network to predict superpixels on a regular image grid. Experimental results on benchmark datasets show that our method achieves state-of-the-art superpixel segmentation performance while running at about 50fps. Based on the predicted superpixels, we further develop a downsampling/upsampling scheme for deep networks with the goal of generating high-resolution outputs for dense prediction tasks. Specifically, we modify a popular network architecture for stereo matching to simultaneously predict superpixels and disparities. We show that improved disparity estimation accuracy can be obtained on public datasets.