Unseen Object Instance Segmentation for Robotic Environments

07/16/2020
by   Christopher Xie, et al.
21

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, UOIS-Net, separately leverages synthetic RGB and synthetic depth for unseen object instance segmentation. UOIS-Net is comprised 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. Secondly, these initial masks are refined using RGB. Surprisingly, our framework is able to learn from synthetic RGB-D data where the RGB is non-photorealistic. 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.

READ FULL TEXT

page 1

page 3

page 6

page 10

page 11

page 13

page 14

page 16

research
07/30/2019

The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation

In order to function in unstructured environments, robots need the abili...
research
04/21/2022

Unseen Object Instance Segmentation with Fully Test-time RGB-D Embeddings Adaptation

Segmenting unseen objects is a crucial ability for the robot since it ma...
research
02/10/2020

Segmenting unseen industrial components in a heavy clutter using rgb-d fusion and synthetic data

Segmentation of unseen industrial parts is essential for autonomous indu...
research
06/29/2021

RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networks

Segmenting unseen object instances in cluttered environments is an impor...
research
03/20/2023

Bimodal SegNet: Instance Segmentation Fusing Events and RGB Frames for Robotic Grasping

Object segmentation for robotic grasping under dynamic conditions often ...
research
09/16/2018

Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Point Clouds

The ability to segment unknown objects in depth images has potential to ...

Please sign up or login with your details

Forgot password? Click here to reset