# Single Pixel Reconstruction for One-stage Instance Segmentation

arXiv: https://arxiv.org/abs/1904.07426 · HTML: https://mlsanity.com/paper/1904.07426/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2019.

## Built on by (most cited first, 6 of 6)

- [ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection](https://mlsanity.com/paper/2111.14055/) (2021)
- [SDTP: Semantic-aware Decoupled Transformer Pyramid for Dense Image Prediction](https://mlsanity.com/paper/2109.08963/) (2021)
- [A Class-wise Non-salient Region Generalized Framework for Video Semantic Segmentation](https://mlsanity.com/paper/2212.14154/) (2022)
- [Synthetic Instance Segmentation from Semantic Image Segmentation Masks](https://mlsanity.com/paper/2308.00949/) (2023)
- [G-Mix: A Generalized Mixup Learning Framework Towards Flat Minima](https://mlsanity.com/paper/2308.03236/) (2023)
- [Cross-modal Context-aware Learning for Visual Prompt Guided Multimodal Image Understanding in Remote Sensing](https://mlsanity.com/paper/2512.11680/) (2025)

## Abstract (arXiv)

Object instance segmentation is one of the most fundamental but challenging tasks in computer vision, and it requires the pixel-level image understanding. Most existing approaches address this problem by adding a mask prediction branch to a two-stage object detector with the Region Proposal Network (RPN). Although producing good segmentation results, the efficiency of these two-stage approaches is far from satisfactory, restricting their applicability in practice. In this paper, we propose a one-stage framework, SPRNet, which performs efficient instance segmentation by introducing a single pixel reconstruction (SPR) branch to off-the-shelf one-stage detectors. The added SPR branch reconstructs the pixel-level mask from every single pixel in the convolution feature map directly. Using the same ResNet-50 backbone, SPRNet achieves comparable mask AP to Mask R-CNN at a higher inference speed, and gains all-round improvements on box AP at every scale comparing with RetinaNet.