SOURCE-LINKED INTELLIGENCE

Mitigating Performance Discrepancy in Cross-Domain 3D Class-Incremental Learning

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

3D perception plays a crucial role in real-world applications such as autonomous driving, robotics, and AR/VR. In practical scenarios, 3D perception models need to continually adapt to newly emerging 3D object categories, making class-incremental learning (CIL) particularly important. However, unlike 2D images, 3D point clouds are inherently heterogeneous: objects from the same class may not only come from the clean CAD domain, but also from RGB-D camera scans of varying quality, video reconstructions, or even corrupted observations. We discover that such heterogeneity introduces a new challen

Read original source ↗ Open in workspace

recordType

paper

region

Global