Most of the buildings that exist today were built based on 2D drawings. Building information
models that represent design-stage product information have become prevalent in the …

We present ScanNet++, a large-scale dataset that couples together capture of high-quality
and commodity-level geometry and color of indoor scenes. Each scene is captured with a …

Existing state-of-the-art 3D instance segmentation methods perform semantic segmentation
followed by grouping. The hard predictions are made when performing semantic …

Modern 3D semantic instance segmentation approaches predominantly rely on specialized
voting mechanisms followed by carefully designed geometric clustering techniques. Building …

Most existing methods realize 3D instance segmentation by extending those models used
for 3D object detection or 3D semantic segmentation. However, these non-straightforward …

We introduce the task of localizing a flexible number of objects in real-world 3D scenes
using natural language descriptions. Existing 3D visual grounding tasks focus on localizing …

For years, researchers have been devoted to generalizable object perception and
manipulation, where cross-category generalizability is highly desired yet underexplored. In …

Abstract 3D visual grounding aims to find the object within point clouds mentioned by free-
form natural language descriptions with rich semantic cues. However, existing methods …

We introduce Open3DIS a novel solution designed to tackle the problem of Open-
Vocabulary Instance Segmentation within 3D scenes. Objects within 3D environments …

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 …