Large-scale 2D foundation models exhibit strong transferable representations, yet extending them to 3D volumetric data typically requires retraining, adapters, or architectural redesign. We introduce PlaneCycle, a training-free, adapter-free operator for architecture-agnostic 2D-to-3D lifting of foundation models. PlaneCycle reuses the original pretrained 2D backbone by cyclically distributing spatial aggregation across orthogonal HW, DW, and DH planes throughout network depth, enabling progressive 3D fusion while preserving pretrained inductive biases. The method introduces no additional parameters and is applicable to arbitrary 2D networks. Using pretrained DINOv3 models, we evaluate PlaneCycle on six 3D classification and three 3D segmentation benchmarks. Without any training, the lifted models exhibit intrinsic 3D fusion capability and, under linear probing, outperform slice-wise 2D baselines and strong 3D counterparts, approaching the performance of fully trained models. With full fine-tuning, PlaneCycle matches standard 3D architectures, highlighting its potential as a seamless and practical 2D-to-3D lifting operator. These results demonstrate that 3D capability can be unlocked from pretrained 2D foundation models without structural modification or retraining. Code is available at https://github.com/HINTLab/PlaneCycle.

翻译：大规模二维基础模型展现出强大的可迁移表征能力，然而将其扩展至三维体数据通常需要重新训练、适配器或架构重新设计。本文提出PlaneCycle，一种无需训练、无需适配器的算子，用于实现架构无关的二维到三维基础模型提升。PlaneCycle通过在网络深度上循环地在正交的HW、DW和DH平面间分布空间聚合操作，重复利用原始预训练的二维骨干网络，从而实现渐进式三维融合，同时保留预训练的归纳偏置。该方法不引入额外参数，适用于任意二维网络。基于预训练的DINOv3模型，我们在六个三维分类和三个三维分割基准上评估PlaneCycle。在无需任何训练的情况下，提升后的模型展现出内在的三维融合能力，并且在线性探测设置下，其性能超越了逐切片二维基线模型和强三维对比模型，接近完全训练模型的水平。通过全微调，PlaneCycle与标准三维架构性能相当，突显了其作为一种无缝且实用的二维到三维提升算子的潜力。这些结果表明，无需结构修改或重新训练，即可从预训练的二维基础模型中解锁三维能力。代码发布于https://github.com/HINTLab/PlaneCycle。