Unseen Object Instance Segmentation
7 papers with code • 2 benchmarks • 2 datasets
Instance segmentation is the task of detecting and delineating each distinct object of interest appearing in an image.
Image Credit: Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers
OCID
WISDOM
Most implemented papers
Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Data
We train a variant of Mask R-CNN with domain randomization on the generated dataset to perform category-agnostic instance segmentation without any hand-labeled data and we evaluate the trained network, which we refer to as Synthetic Depth (SD) Mask R-CNN, on a set of real, high-resolution depth images of challenging, densely-cluttered bins containing objects with highly-varied geometry.
Segmenting Unseen Industrial Components in a Heavy Clutter Using RGB-D Fusion and Synthetic Data
Segmentation of unseen industrial parts is essential for autonomous industrial systems.
Unseen Object Instance Segmentation for Robotic Environments
chrisdxie/uois
•
•
We also show that our method can segment unseen objects for robot grasping.
Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation
NVlabs/UnseenObjectClustering
•
•
In this work, we propose a new method for unseen object instance segmentation by learning RGB-D feature embeddings from synthetic data.
Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling
gist-ailab/uoais
•
•
Instance-aware segmentation of unseen objects is essential for a robotic system in an unstructured environment.
Mean Shift Mask Transformer for Unseen Object Instance Segmentation
youngsean/unseenobjectswithmeanshift
•
•
To illustrate the effectiveness of our method, we apply MSMFormer to unseen object instance segmentation.
Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction
youngsean/unseenobjectswithmeanshift
•
•
By applying multi-object tracking and video object segmentation on the images collected via robot pushing, our system can generate segmentation masks of all the objects in these images in a self-supervised way.
