SRDA: Generating Instance Segmentation Annotation via Scanning, Reasoning and Domain Adaptation

Wenqiang Xu, Yonglu Li, Cewu Lu; Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 120-136

Abstract


Instance segmentation is a problem of significance in computer vision. However, preparing annotated data for this task is extremely time-consuming and costly. By combining the advantages of 3D scanning, reasoning, and GAN-based domain adaptation techniques, we introduce a novel pipeline named SRDA to obtain large quantities of training samples with very minor effort. Our pipeline is well-suited to scenes that can be scanned, i.e. most indoor and some outdoor scenarios. To evaluate our performance, we build three representative scenes and a new dataset, with 3D models of various common objects categories and annotated real-world scene images. Extensive experiments show that our pipeline can achieve decent instance segmentation performance given very low human labor cost.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2018_ECCV,
author = {Xu, Wenqiang and Li, Yonglu and Lu, Cewu},
title = {SRDA: Generating Instance Segmentation Annotation via Scanning, Reasoning and Domain Adaptation},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
month = {September},
year = {2018}
}