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

Abstract

In order to function in unstructured environments, robots need the ability to recognize unseen novel 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. We propose a novel method that separately leverages synthetic RGB and synthetic depth for unseen object instance segmentation. Our method is comprised of two stages where the first stage operates only on depth to produce rough initial masks, and the second stage refines these masks with 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, trained on this dataset, can produce sharp and accurate 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. Code, models and video can be found at https://rse-lab.cs.washington.edu/projects/unseen-object-instance-segmentation/.

References in corpus (7)

• Learning to Segment Object Candidates
• Semantic Instance Segmentation with a Discriminative Loss Function
• The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
• Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics
• Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects
• Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control
• ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors

Cited by in corpus (5)

• Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation
• iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes
• Unseen Object Instance Segmentation for Robotic Environments
• SORNet: Spatial Object-Centric Representations for Sequential Manipulation
• Relevance-Guided Modeling of Object Dynamics for Reinforcement Learning