Towards Model Generalization for Monocular 3D Object Detection. (arXiv:2205.11664v3 [cs.CV] UPDATED)

Monocular 3D object detection (Mono3D) has achieved tremendous improvements
with emerging large-scale autonomous driving datasets and the rapid development
of deep learning techniques. However, caused by severe domain gaps (e.g., the
field of view (FOV), pixel size, and object size among datasets), Mono3D
detectors have difficulty in generalization, leading to drastic performance
degradation on unseen domains. To solve these issues, we combine the
position-invariant transform and multi-scale training with the pixel-size depth
strategy to construct an effective unified camera-generalized paradigm …

3d arxiv cv detection model generalization