SODA: Out-of-Distribution Detection in Domain-Shifted Point Clouds via Neighborhood Propagation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908425389080576 |
|---|---|
| author | Goodge, Adam Xu, Xun Hooi, Bryan Ng, Wee Siong Liao, Jingyi Su, Yongyi Yang, Xulei |
| author_facet | Goodge, Adam Xu, Xun Hooi, Bryan Ng, Wee Siong Liao, Jingyi Su, Yongyi Yang, Xulei |
| contents | As point cloud data increases in prevalence in a variety of applications, the ability to detect out-of-distribution (OOD) point cloud objects becomes critical for ensuring model safety and reliability. However, this problem remains under-explored in existing research. Inspired by success in the image domain, we propose to exploit advances in 3D vision-language models (3D VLMs) for OOD detection in point cloud objects. However, a major challenge is that point cloud datasets used to pre-train 3D VLMs are drastically smaller in size and object diversity than their image-based counterparts. Critically, they often contain exclusively computer-designed synthetic objects. This leads to a substantial domain shift when the model is transferred to practical tasks involving real objects scanned from the physical environment. In this paper, our empirical experiments show that synthetic-to-real domain shift significantly degrades the alignment of point cloud with their associated text embeddings in the 3D VLM latent space, hindering downstream performance. To address this, we propose a novel methodology called SODA which improves the detection of OOD point clouds through a neighborhood-based score propagation scheme. SODA is inference-based, requires no additional model training, and achieves state-of-the-art performance over existing approaches across datasets and problem settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_21892 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SODA: Out-of-Distribution Detection in Domain-Shifted Point Clouds via Neighborhood Propagation Goodge, Adam Xu, Xun Hooi, Bryan Ng, Wee Siong Liao, Jingyi Su, Yongyi Yang, Xulei Computer Vision and Pattern Recognition Artificial Intelligence As point cloud data increases in prevalence in a variety of applications, the ability to detect out-of-distribution (OOD) point cloud objects becomes critical for ensuring model safety and reliability. However, this problem remains under-explored in existing research. Inspired by success in the image domain, we propose to exploit advances in 3D vision-language models (3D VLMs) for OOD detection in point cloud objects. However, a major challenge is that point cloud datasets used to pre-train 3D VLMs are drastically smaller in size and object diversity than their image-based counterparts. Critically, they often contain exclusively computer-designed synthetic objects. This leads to a substantial domain shift when the model is transferred to practical tasks involving real objects scanned from the physical environment. In this paper, our empirical experiments show that synthetic-to-real domain shift significantly degrades the alignment of point cloud with their associated text embeddings in the 3D VLM latent space, hindering downstream performance. To address this, we propose a novel methodology called SODA which improves the detection of OOD point clouds through a neighborhood-based score propagation scheme. SODA is inference-based, requires no additional model training, and achieves state-of-the-art performance over existing approaches across datasets and problem settings. |
| title | SODA: Out-of-Distribution Detection in Domain-Shifted Point Clouds via Neighborhood Propagation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2506.21892 |