Unseen Object Instance Segmentation for Robotic Environments

By Christopher Xie, Yu Xiang, Arsalan Mousavian, Dieter Fox. 2020

153 citations recorded by the source corpus.

In order to function in unstructured environments, robots need the ability to recognize unseen objects. We take a step in this direction by tackling the problem of segmenting unseen object instances in tabletop environments. However, the type of large-scale real-world dataset required for this task typically does not exist for most robotic settings, which motivates the use of synthetic data. Our proposed method, unseen object instance segmentation (UOIS)-Net, separately leverages synthetic RGB and synthetic depth for unseen object instance segmentation. UOIS-Net is composed of two stages: first, it operates only on depth to produce object instance center votes in 2D or 3D and assembles them into rough initial masks. Second, these initial masks are refined using RGB. Surprisingly, our framework is able to learn from synthetic RGB-D data where the RGB is nonphotorealistic. To train our method, we introduce a large-scale synthetic dataset of random objects on tabletops. We show that our method can produce sharp and accurate segmentation masks, outperforming state-of-the-art methods on unseen object instance segmentation. We also show that our method can segment unseen objects for robot grasping.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Dieter Fox
2. Arsalan Mousavian
3. Rudolph Triebel
4. Martin Sundermeyer
5. Yu Xiang
6. Anelia Angelova
7. Zoltán-Csaba Márton
8. In-So Kweon

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Jitendra Malik
3. Dacheng Tao
4. Xiaogang Wang
5. Trevor Darrell
6. Kristen Grauman
7. Ming-Hsuan Yang
8. Andrew Zisserman

In Control and Systems Engineering

1. Dieter Fox
2. Arsalan Mousavian
3. Christopher Xie
4. Yu Xiang
5. Martin Sundermeyer
6. Rudolph Triebel
7. Anelia Angelova
8. Zoltán-Csaba Márton

In Robotics & Control

1. Dieter Fox
2. Arsalan Mousavian
3. Yu Xiang
4. Christopher Xie
5. Zoltán-Csaba Márton
6. Andy Zeng

Citations in the corpus

• Learning Open-World Object Proposals without Learning to Classify (2021, background): “The objectness is often trained on synthetic RGB and depth data [38], [39] or on”
• Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation (2020, background): “Future work could investigate how to fix there failures using multi-view images or active perception with robots.”
• Unknown Object Segmentation from Stereo Images (2021, methodology): “Even anchor-free methods [9], [10] then require expensive post-processing steps such as Non-Maximum Suppression [11], watershed algorithm [12], hough-voting [13], or clustering [14], [15] to filter the raw network outputs.”