Amodal Instance Segmentation
7 papers with code • 0 benchmarks • 0 datasets
Different from traditional segmentation which only focuses on visible regions, amodal instance segmentation also predicts the occluded parts of object instances.
Description Credit: Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers, CVPR'21
These leaderboards are used to track progress in Amodal Instance Segmentation
LibrariesUse these libraries to find Amodal Instance Segmentation models and implementations
Semantic amodal segmentation is a recently proposed extension to instance-aware segmentation that includes the prediction of the invisible region of each object instance.
Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation
Specifically, we first introduce a new representation, namely a semantics-aware distance map (sem-dist map), to serve as our target for amodal segmentation instead of the commonly used masks and heatmaps.
The proposed method extends upon the representational output of semantic instance segmentation by explicitly including both visible and occluded parts.
Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model
Moreover, by leveraging an outlier process, Bayesian models can further generalize out-of-distribution to segment partially occluded objects and to predict their amodal object boundaries.
Segmenting highly-overlapping objects is challenging, because typically no distinction is made between real object contours and occlusion boundaries.
Instance-aware segmentation of unseen objects is essential for a robotic system in an unstructured environment.