SOURCE-LINKED INTELLIGENCE

MAETrack: Unleashing the Potential of Pretrained Geometric Priors for 3D Single Object Tracking

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Large-scale pre-training has transformed representation learning in 2D vision, yet its transferability to 3D single object tracking (SOT) remains insufficiently understood. Directly fine-tuning self-supervised 3D encoders, such as masked autoencoders (MAE), often leads to sub-optimal adaptation because the reconstruction objective is not fully aligned with the spatial-temporal matching requirements of tracking. In this paper, we observe that this difficulty can be interpreted as a layer-wise transfer mismatch: shallow layers tend to preserve transferable geometric cues, while deeper layers bec

Read original source ↗ Open in workspace

recordType

paper

region

Global