Generalizable 3D part segmentation is important but challenging in vision and robotics.
Training deep models via conventional supervised methods requires large-scale 3D …

We, as human beings, can understand and picture a familiar scene from arbitrary viewpoints
given a single image, whereas this is still a grand challenge for computers. We hereby …

Open-world 3D part segmentation is pivotal in diverse applications such as robotics and
AR/VR. Traditional supervised methods often grapple with limited 3D data availability and …

This paper proposes a shape anchor guided learning strategy (AncLearn) for robust holistic
indoor scene understanding. We observe that the search space constructed by current …

We present ANISE, a method that reconstructs a 3D shape from partial observations (images
or sparse point clouds) using a part-aware neural implicit shape representation. The shape …

Existing methods for reconstructing interactive scenes primarily focus on replacing
reconstructed objects with CAD models retrieved from a limited database, resulting in …

Abstract 3D scene understanding has seen significant advances in recent years, but has
largely focused on object understanding in 3D scenes with independent per-object …

We propose Scan2Part, a method to segment individual parts of objects in real-world, noisy
indoor RGB-D scans. To this end, we vary the part hierarchies of objects in indoor scenes …

Extracting indoor scene components (ie, the meaningful parts of indoor objects) and
obtaining their spatial relationships (eg, adjacent, in the left of, etc.) is crucial for scene …

This research focuses on the possibility of building an alternative mixed reality (MR) system,
which will eliminate all its main causes of visual discomfort and form a model of the real …