Unseen Object Instance Segmentation
2개 벤치마크 · 논문 14편 · 이 태스크의 논문 보기 →
Benchmarks
Most implemented
Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Data
High-Quality Unknown Object Instance Segmentation via Quadruple Boundary Error Refinement
Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction
Mean Shift Mask Transformer for Unseen Object Instance Segmentation
Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation
Papers
rt-RISeg: Real-Time Model-Free Robot Interactive Segmentation for Active Instance-Level Object Understanding
Successful execution of dexterous robotic manipulation tasks in new environments, such as grasping, depends on the ability to proficiently segment unseen objects from the background and other objects. Previous works in u…
Unseen Object Instance SegmentationInteractive SegmentationObject SegmentationZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments with Vision Foundation Models
Service robots operating in unstructured environments must effectively recognize and segment unknown objects to enhance their functionality. Traditional supervised learningbased segmentation techniques require extensive …
Instance SegmentationObjectSegmentationSemantic Segmentation+1Adapting Segment Anything Model for Unseen Object Instance Segmentation
Unseen Object Instance Segmentation (UOIS) is crucial for autonomous robots operating in unstructured environments. Previous approaches require full supervision on large-scale tabletop datasets for effective pretraining.…
DecoderInstance SegmentationSegmentationSemantic Segmentation+1RISeg: Robot Interactive Object Segmentation via Body Frame-Invariant Features
In order to successfully perform manipulation tasks in new environments, such as grasping, robots must be proficient in segmenting unseen objects from the background and/or other objects. Previous works perform unseen ob…
Instance SegmentationObjectSegmentationSemantic Segmentation+1High-Quality Unknown Object Instance Segmentation via Quadruple Boundary Error Refinement
Accurate and efficient segmentation of unknown objects in unstructured environments is essential for robotic manipulation. Unknown Object Instance Segmentation (UOIS), which aims to identify all objects in unknown catego…
Instance SegmentationObjectSegmentationSemantic Segmentation+1Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction
We introduce a novel robotic system for improving unseen object instance segmentation in the real world by leveraging long-term robot interaction with objects. Previous approaches either grasp or push an object and then …
Instance SegmentationMulti-Object TrackingObjectObject Tracking+6