Current 3D scene segmentation methods are heavily dependent on manually annotated 3D
training datasets. Such manual annotations are labor-intensive, and often lack fine-grained …

3D segmentation is a fundamental and challenging problem in computer vision with
applications in autonomous driving and robotics. It has received significant attention from the …

Category-level 6D object pose estimation aims to estimate the rotation translation and size
of unseen instances within specific categories. In this area dense correspondence-based …

Abstract 3D instance segmentation (3DIS) is a crucial task but point-level annotations are
tedious in fully supervised settings. Thus using bounding boxes (bboxes) as annotations has …

State-of-the-art models on contemporary 3D segmentation benchmarks like ScanNet
consume and label dataset-provided 3D point clouds obtained through post processing of …

While recent 3D instance segmentation approaches show promising results based on
transformer architectures they often fail to correctly identify instances with similar …

We propose UniSeg3D, a unified 3D segmentation framework that achieves panoptic,
semantic, instance, interactive, referring, and open-vocabulary semantic segmentation tasks …

Thanks to its precise spatial referencing, 3D point cloud visual grounding is essential for
deep understanding and dynamic interaction in 3D environments, encompassing 3D …

Coarse-to-fine 3D instance segmentation methods show weak performances compared to
recent Grouping-based Kernel-based and Transformer-based methods. We argue that this is …

Unsupervised point cloud shape correspondence aims to establish point-wise
correspondences between source and target point clouds. Existing methods obtain …