CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models

Can you segment the common object in these images? The common object is the dog. Both images show a dog. The common part is the head. The images show a dog. The unique parts are the neck (IMAGE1), the leg, the foot, the body, and the tail (IMAGE2). Common Parts: Please segment the common parts of the objects. Unique Parts: What are the unique parts of the objects in these images? Please output segmentation masks. CALICO Figure 1. Multi-Image Part-focused Object Comparison with CALICO. Our pixel-grounded Large Vision-Language Model, CALICO, performs part-focused semantic co-segmentation, a newly introduced task where the goal is to identify, segment, and label common objects, as well as common and unique object parts across multiple images.