Rank-DETR for high quality object detection

Y Pu, W Liang, Y Hao, Y Yuan… - Advances in …, 2024 - proceedings.neurips.cc
Modern detection transformers (DETRs) use a set of object queries to predict a list of
bounding boxes, sort them by their classification confidence scores, and select the top …

[HTML][HTML] Advancements in point cloud-based 3D defect classification and segmentation for industrial systems: A comprehensive survey

A Rani, D Ortiz-Arroyo, P Durdevic - Information Fusion, 2024 - Elsevier
In recent years, 3D point clouds (PCs) have gained significant attention due to their diverse
applications across various fields, such as computer vision (CV), condition monitoring (CM) …

Segpoint: Segment any point cloud via large language model

S He, H Ding, X Jiang, B Wen - European Conference on Computer Vision, 2024 - Springer
Despite significant progress in 3D point cloud segmentation, existing methods primarily
address specific tasks and depend on explicit instructions to identify targets, lacking the …

3d-gres: Generalized 3d referring expression segmentation

C Wu, Y Liu, J Ji, Y Ma, H Wang, G Luo… - Proceedings of the …, 2024 - dl.acm.org
3D Referring Expression Segmentation (3D-RES) is dedicated to segmenting a specific
instance within a 3D space based on a natural language description. However, current …

RefMask3D: Language-guided transformer for 3D referring segmentation

S He, H Ding - Proceedings of the 32nd ACM International …, 2024 - dl.acm.org
3D referring segmentation is an emerging and challenging vision-language task that aims to
segment the object described by a natural language expression in a point cloud scene. The …

ODIN: A Single Model for 2D and 3D Segmentation

A Jain, P Katara, N Gkanatsios… - Proceedings of the …, 2024 - openaccess.thecvf.com
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 …

Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior

W Roh, H Jung, G Nam, J Yeom… - Proceedings of the …, 2024 - openaccess.thecvf.com
While recent 3D instance segmentation approaches show promising results based on
transformer architectures they often fail to correctly identify instances with similar …