PolyTransform: Deep Polygon Transformer for Instance Segmentation
| Autor: | Wei-Chiu Ma, Namdar Homayounfar, Yuwen Xiong, Justin Liang, Raquel Urtasun, Rui Hu |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
business.industry Computer science Computer Vision and Pattern Recognition (cs.CV) Feature extraction Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Image segmentation 010501 environmental sciences 01 natural sciences law.invention law Polygon 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Segmentation Artificial intelligence business Transformer 0105 earth and related environmental sciences |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr42600.2020.00915 |
| Popis: | In this paper, we propose PolyTransform, a novel instance segmentation algorithm that produces precise, geometry-preserving masks by combining the strengths of prevailing segmentation approaches and modern polygon-based methods. In particular, we first exploit a segmentation network to generate instance masks. We then convert the masks into a set of polygons that are then fed to a deforming network that transforms the polygons such that they better fit the object boundaries. Our experiments on the challenging Cityscapes dataset show that our PolyTransform significantly improves the performance of the backbone instance segmentation network and ranks 1st on the Cityscapes test-set leaderboard. We also show impressive gains in the interactive annotation setting. We release the code at https://github.com/uber-research/PolyTransform. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|