Self-supervised Transparent Liquid Segmentation for Robotic Pouring
This addresses the challenge of liquid state estimation for robotics, specifically in pouring tasks, by providing a method that avoids manual labeling, though it is incremental as it builds on existing segmentation and generative techniques.
The paper tackles the problem of segmenting transparent liquids like water from static RGB images without manual annotations, using a generative model to translate colored liquid images into synthetic transparent ones and achieving accurate segmentation masks for robotic pouring tasks.
Liquid state estimation is important for robotics tasks such as pouring; however, estimating the state of transparent liquids is a challenging problem. We propose a novel segmentation pipeline that can segment transparent liquids such as water from a static, RGB image without requiring any manual annotations or heating of the liquid for training. Instead, we use a generative model that is capable of translating images of colored liquids into synthetically generated transparent liquid images, trained only on an unpaired dataset of colored and transparent liquid images. Segmentation labels of colored liquids are obtained automatically using background subtraction. Our experiments show that we are able to accurately predict a segmentation mask for transparent liquids without requiring any manual annotations. We demonstrate the utility of transparent liquid segmentation in a robotic pouring task that controls pouring by perceiving the liquid height in a transparent cup. Accompanying video and supplementary materials can be found