Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning Article Swipe

MAKE IMPACT

Yang Li , Aming Wu , Zihao Zhang , Yahong Han · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2510.13307

In this paper, we focus on Novel Class Discovery for Point Cloud Segmentation (3D-NCD), aiming to learn a model that can segment unlabeled (novel) 3D classes using only the supervision from labeled (base) 3D classes. The key to this task is to setup the exact correlations between the point representations and their base class labels, as well as the representation correlations between the points from base and novel classes. A coarse or statistical correlation learning may lead to the confusion in novel class inference. lf we impose a causal relationship as a strong correlated constraint upon the learning process, the essential point cloud representations that accurately correspond to the classes should be uncovered. To this end, we introduce a structural causal model (SCM) to re-formalize the 3D-NCD problem and propose a new method, i.e., Joint Learning of Causal Representation and Reasoning. Specifically, we first analyze hidden confounders in the base class representations and the causal relationships between the base and novel classes through SCM. We devise a causal representation prototype that eliminates confounders to capture the causal representations of base classes. A graph structure is then used to model the causal relationships between the base classes' causal representation prototypes and the novel class prototypes, enabling causal reasoning from base to novel classes. Extensive experiments and visualization results on 3D and 2D NCD semantic segmentation demonstrate the superiorities of our method.

Type

preprint

Landing Page

http://arxiv.org/abs/2510.13307

PDF

https://arxiv.org/pdf/2510.13307

OA Status

green

OpenAlex ID

https://openalex.org/W4415275671

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4415275671

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2510.13307

Digital Object Identifier

Title

Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning

Work title

Type

preprint

OpenAlex work type

Publication year

2025

Year of publication

Publication date

2025-10-15

Full publication date if available

Authors

Yang Li, Aming Wu, Zihao Zhang, Yahong Han

List of authors in order

Landing page

https://arxiv.org/abs/2510.13307

Publisher landing page

PDF URL

https://arxiv.org/pdf/2510.13307

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2510.13307

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload