AI RESEARCH
Counting Through Occlusion: Framework for Open World Amodal Counting
arXiv CS.CV
•
ArXi:2511.12702v2 Announce Type: replace Object counting has achieved remarkable success on visible instances, yet state-of-the-art (SOTA) methods fail under occlusion. This failure stems from a fundamental architectural limitation where backbone networks encode occluding surfaces rather than target objects, thereby corrupting the feature representations required for accurate enumeration. To address this, we present CountOCC, an amodal counting framework that explicitly reconstructs occluded object features through hierarchical multimodal guidance.