Construction and maintenance of building geometric digital twins: state of the art review

V Drobnyi, Z Hu, Y Fathy, I Brilakis - Sensors, 2023 - mdpi.com
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 …

Scannet++: A high-fidelity dataset of 3d indoor scenes

C Yeshwanth, YC Liu, M Nießner… - Proceedings of the …, 2023 - openaccess.thecvf.com
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 …

Softgroup for 3d instance segmentation on point clouds

T Vu, K Kim, TM Luu, T Nguyen… - Proceedings of the …, 2022 - openaccess.thecvf.com
Existing state-of-the-art 3D instance segmentation methods perform semantic segmentation
followed by grouping. The hard predictions are made when performing semantic …

Mask3d: Mask transformer for 3d semantic instance segmentation

J Schult, F Engelmann, A Hermans… - … on Robotics and …, 2023 - ieeexplore.ieee.org
Modern 3D semantic instance segmentation approaches predominantly rely on specialized
voting mechanisms followed by carefully designed geometric clustering techniques. Building …

Superpoint transformer for 3d scene instance segmentation

J Sun, C Qing, J Tan, X Xu - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
Most existing methods realize 3D instance segmentation by extending those models used
for 3D object detection or 3D semantic segmentation. However, these non-straightforward …

Multi3drefer: Grounding text description to multiple 3d objects

Y Zhang, ZM Gong, AX Chang - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
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 …

Gapartnet: Cross-category domain-generalizable object perception and manipulation via generalizable and actionable parts

H Geng, H Xu, C Zhao, C Xu, L Yi… - Proceedings of the …, 2023 - openaccess.thecvf.com
For years, researchers have been devoted to generalizable object perception and
manipulation, where cross-category generalizability is highly desired yet underexplored. In …

Eda: Explicit text-decoupling and dense alignment for 3d visual grounding

Y Wu, X Cheng, R Zhang, Z Cheng… - Proceedings of the …, 2023 - openaccess.thecvf.com
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 …

Open3dis: Open-vocabulary 3d instance segmentation with 2d mask guidance

P Nguyen, TD Ngo, E Kalogerakis… - Proceedings of the …, 2024 - openaccess.thecvf.com
We introduce Open3DIS a novel solution designed to tackle the problem of Open-
Vocabulary Instance Segmentation within 3D scenes. Objects within 3D environments …

Segment3d: Learning fine-grained class-agnostic 3d segmentation without manual labels

R Huang, S Peng, A Takmaz, F Tombari… - … on Computer Vision, 2025 - Springer
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 …