Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning

Remco Leijenaar (University of Groningen) · Hamidreza Kasaei (Dept. of AI, University of Groningen)

3d point cloudsasymmetric dual self-distillationasymmetric setuphigh-level semanticsjoint embedding architecturemasked point modelingmasked queriesmulti-cropmulti-mask samplingpoint cloud adaptationreconstruction-based objectivescanobjectnnself-supervised learningsemantically meaningful representationsshape leakagestate-of-the-art results

Learning semantically meaningful representations from unstructured 3D point clouds remains a central challenge in computer vision, especially in the absence of large-scale labeled datasets. While masked point modeling (MPM) is widely used in self-supervised 3D learning, its reconstruction-based objective can limit its ability to capture high-level semantics. We propose AsymDSD, an Asymmetric Dual Self-Distillation framework that unifies masked modeling and invariance learning through prediction in the latent space rather than the input space. AsymDSD builds on a joint embedding architecture and introduces several key design choices: an efficient asymmetric setup, disabling attention between masked queries to prevent shape leakage, multi-mask sampling, and a point cloud adaptation of multi-crop. AsymDSD achieves state-of-the-art results on ScanObjectNN (90.53\%) and further improves to 93.72\% when pretrained on 930k shapes, surpassing prior methods.