3D Segmentation Using Viewpoint-Dependent Spatial Relationships

ArXi:2605.15708v1 Announce Type: new Recent advances in 3D datasets and multimodal models have greatly improved natural language 3D scene understanding. However, most 3D referring segmentation methods do not explicitly represent the observer viewpoint, making spatial relations such as "left," "right," "front," and "behind" ambiguous and difficult to evaluate. We