Recent advances in multi-modal 3D scene understanding: A comprehensive survey and evaluation

Y Lei, Z Wang, F Chen, G Wang, P Wang… - arxiv preprint arxiv …, 2023 - arxiv.org
Multi-modal 3D scene understanding has gained considerable attention due to its wide
applications in many areas, such as autonomous driving and human-computer interaction …

Learning to adapt sam for segmenting cross-domain point clouds

X Peng, R Chen, F Qiao, L Kong, Y Liu, Y Sun… - … on Computer Vision, 2024 - Springer
Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable
challenge, primarily steming from the sparse and unordered nature of point clouds …

Moho: Learning single-view hand-held object reconstruction with multi-view occlusion-aware supervision

C Zhang, G Jiao, Y Di, G Wang… - Proceedings of the …, 2024 - openaccess.thecvf.com
Previous works concerning single-view hand-held object reconstruction typically rely on
supervision from 3D ground-truth models which are hard to collect in real world. In contrast …

Clip2uda: Making frozen clip reward unsupervised domain adaptation in 3d semantic segmentation

Y Wu, M **ng, Y Zhang, Y **e, Y Qu - Proceedings of the 32nd ACM …, 2024 - dl.acm.org
Multi-modal Unsupervised Domain Adaptation (MM-UDA) for large-scale 3D semantic
segmentation involves adapting 2D and 3D models to a target domain without labels, which …

3d weakly supervised semantic segmentation with 2d vision-language guidance

X Xu, Y Yuan, J Li, Q Zhang, Z Jie, L Ma, H Tang… - … on Computer Vision, 2024 - Springer
In this paper, we propose 3DSS-VLG, a weakly supervised approach for 3D S emantic S
egmentation with 2D V ision-L anguage G uidance, an alternative approach that a 3D model …

Visual foundation models boost cross-modal unsupervised domain adaptation for 3d semantic segmentation

J Xu, W Yang, L Kong, Y Liu, R Zhang, Q Zhou… - arxiv preprint arxiv …, 2024 - arxiv.org
Unsupervised domain adaptation (UDA) is vital for alleviating the workload of labeling 3D
point cloud data and mitigating the absence of labels when facing a newly defined domain …

Model2scene: Learning 3d scene representation via contrastive language-cad models pre-training

R Chen, X Zhu, N Chen, D Wang, W Li, Y Ma… - arxiv preprint arxiv …, 2023 - arxiv.org
Current successful methods of 3D scene perception rely on the large-scale annotated point
cloud, which is tedious and expensive to acquire. In this paper, we propose Model2Scene, a …

Sam-guided unsupervised domain adaptation for 3d segmentation

X Peng, R Chen, F Qiao, L Kong, Y Liu, T Wang… - arxiv preprint arxiv …, 2023 - arxiv.org
Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable
challenge, primarily stemming from the sparse and unordered nature of point cloud data …

Domain-specific information preservation for Alzheimer's disease diagnosis with incomplete multi-modality neuroimages

H Xu, J Wang, Q Feng, Y Zhang, Z Ning - Medical Image Analysis, 2025 - Elsevier
Although multi-modality neuroimages have advanced the early diagnosis of Alzheimer's
Disease (AD), missing modality issue still poses a unique challenge in the clinical practice …

Point Cloud Semantic Segmentation by Adaptively Fusing Information With Varying Distances

Z Jiang, B Yao, K Song, X Qiu… - IEEE Signal Processing …, 2024 - ieeexplore.ieee.org
Point clouds provide rich geometric representations, and point cloud semantic segmentation
is essential in many applications. As the data scale of point clouds is usually quite large …