Contrastive image-to-LiDAR knowledge transfer, commonly used for learning 3D
representations with synchronized images and point clouds, often faces a
self-conflict dilemma. This issue arises as contrastive losses unintentionally
dissociate features of unmatched points and pixels that share semantic labels,
compromising the integrity of learned representations. To overcome this, we
harness Visual Foundation Models (VFMs), which have revolutionized the
acquisition of pixel-level semantics, to enhance 3D representation learning.
Specifically, we utilize off-the-shelf VFMs to generate semantic labels for
weakly-supervised pixel-to-point contrastive distillation. Additionally, we
employ von Mises-Fisher distributions to structure the feature space, ensuring
semantic embeddings within the same class remain consistent across varying
inputs. Furthermore, we adapt sampling probabilities of points to address
imbalances in spatial distribution and category frequency, promoting
comprehensive and balanced learning. Extensive experiments demonstrate that our
approach mitigates the challenges posed by traditional methods and consistently
surpasses existing image-to-LiDAR contrastive distillation methods in
downstream tasks. The source code is available at
\href{https://github.com/Eaphan/OLIVINE.}{\color{black}this https URL}.

通过利用 VFMs 的像素级语义增强三维表示学习，采用 von Mises-Fisher 分布对特征空间进行结构化，以解决对手法的挑战并在下游任务中始终优于现有的图像到 LiDAR 对比蒸馏方法。