SOTAVerified

Unseen Object Instance Segmentation

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–13 of 13 papers

TitleStatusHype
Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot InteractionCode1
Learning RGB-D Feature Embeddings for Unseen Object Instance SegmentationCode1
Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion ModelingCode1
Mean Shift Mask Transformer for Unseen Object Instance SegmentationCode1
High-Quality Unknown Object Instance Segmentation via Quadruple Boundary Error RefinementCode1
Unseen Object Instance Segmentation for Robotic EnvironmentsCode1
Segmenting Unseen Industrial Components in a Heavy Clutter Using RGB-D Fusion and Synthetic DataCode1
Adapting Segment Anything Model for Unseen Object Instance Segmentation—0
RISeg: Robot Interactive Object Segmentation via Body Frame-Invariant Features—0
The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation—0
Unseen Object Instance Segmentation with Fully Test-time RGB-D Embeddings Adaptation—0
ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments with Vision Foundation ModelsCode0
Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic DataCode0
Show:102550

No leaderboard results yet.