# Spatial Sampling Network for Fast Scene Understanding

arXiv: https://arxiv.org/abs/1905.09033 · HTML: https://mlsanity.com/paper/1905.09033/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2019.

## Built on by (most cited first, 5 of 5)

- [CenterPoly: real-time instance segmentation using bounding polygons](https://mlsanity.com/paper/2108.08923/) (2021)
- [Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2212.12402/) (2022)
- [Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks](https://mlsanity.com/paper/2103.03435/) (2021)
- [Real-time instance segmentation with polygons using an Intersection-over-Union loss](https://mlsanity.com/paper/2305.05490/) (2023)
- [CenterDisks: Real-time instance segmentation with disk covering](https://mlsanity.com/paper/2403.03296/) (2024)

## Abstract (arXiv)

We propose a network architecture to perform efficient scene understanding. This work presents three main novelties: the first is an Improved Guided Upsampling Module that can replace in toto the decoder part in common semantic segmentation networks. Our second contribution is the introduction of a new module based on spatial sampling to perform Instance Segmentation. It provides a very fast instance segmentation, needing only thresholding as post-processing step at inference time. Finally, we propose a novel efficient network design that includes the new modules and test it against different datasets for outdoor scene understanding. To our knowledge, our network is one of the themost efficient architectures for scene understanding published to date, furthermore being 8.6% more accurate than the fastest competitor on semantic segmentation and almost five times faster than the most efficient network for instance segmentation.