Accurate 3D object detection from images can be hindered by inherent depth ambiguity. While knowledge distillation (KD) from privileged sensors such as LiDAR offers a promising direction, it often suffers from a critical cross-sensor domain gap. To address this, we introduce DK3D, a novel depth-aware knowledge distillation framework for 3D detection. Our core strategy involves providing the teacher with privileged ground-truth depth during training. This directly avoids the feature representation mismatch and subsequent inefficient knowledge transfer required when distilling from a LiDAR teacher (sparse, geometric) to a camera-based student (dense, semantic). DK3D introduces specialized modules tailored for two primary student paradigms. For depth-assisted models, we employ a channel-wise projection layer (CPL) and an adversarial scoring block (ASB) to align intermediate features at both the pixel and distribution levels. For depth-independent models, a novel vision-depth association module allows the student to implicitly reason about geometry by fusing depth cues with visual features. Both approaches are further enhanced by target-aware spatial response distillation, which captures complex inter-object spatial relationships. Extensive experiments on the KITTI and nuScenes benchmarks demonstrate that DK3D significantly improves performance for both monocular and multi-view 3D detection, outperforming state-of-the-art methods. As a versatile, plug-and-play framework, DK3D boosts existing models without requiring additional training data or increasing the computational cost at inference.
Building similarity graph...
Analyzing shared references across papers
Loading...
Zizhang Wu
Fan Song
Yuanzhu Gan
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fudan University
Megvii (China)
Vi Technology (United States)
Building similarity graph...
Analyzing shared references across papers
Loading...
Wu et al. (Wed,) studied this question.
www.synapsesocial.com/papers/68c1a8fe54b1d3bfb60e1b00 — DOI: https://doi.org/10.1109/tpami.2025.3594805