Adversarial Large-Scale Root Gap Inpainting

Hao Chen, Mario Valerio Giuffrida, Peter Doerner, Sotirios A. Tsaftaris; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 0-0


Root imaging of a growing plant in a non-invasive, affordable, and effective way remains challenging. One approach is to image roots by growing them in a rhizobox, a soil-filled transparent container, imaging them with digital cameras, and segmenting root from soil background. However, due to soil occlusion and the fact that digital imaging is a 2D projection of a 3D object, gaps are present on the segmentation masks, which may hinder the extraction of finely grained root system architecture (RSA) traits. Herein, we develop an image inpainting technique to recover gaps from disconnected root segments. We train a patch-based deep fully convolutional network using a supervised loss but also use adversarial mechanisms at patch and whole root level. We use Policy Gradient method, to endow the model with large-scale whole root view during training. We train our model using synthetic root data. In our experiments, we show that using adversarial mechanisms at local and whole-root level we obtain a 72% improvement in performance on recovering gaps of real chickpea data when using only patch-level supervision.

Related Material

author = {Chen, Hao and Valerio Giuffrida, Mario and Doerner, Peter and Tsaftaris, Sotirios A.},
title = {Adversarial Large-Scale Root Gap Inpainting},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}