Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image

Understand

Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box.

• We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold.
• In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder.
• We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder-decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process.