We propose a simple yet effective approach to enhance the performance of feed-forward 3D reconstruction models. Existing methods often struggle near depth discontinuities, where standard regression losses encourage spatial averaging and thus blur sharp boundaries. To address this issue, we introduce a mixture-of-experts formulation that handles uncertainty at depth boundaries by combining multiple smooth depth predictions. A softmax weighting head dynamically selects among these hypotheses on a per-pixel basis. By integrating our mixture model into a pre-trained state-of-the-art 3D model, we achieve a substantial reduction of boundary artifacts and gains in overall reconstruction accuracy. Notably, our approach is highly compute efficient, delivering generalizable improvements even when fine-tuned on a small subset of training data while incurring only negligible additional inference computation, suggesting a promising direction for lightweight and accurate 3D reconstruction.

翻译：我们提出了一种简单而有效的方法来提升前馈式三维重建模型的性能。现有方法在深度不连续区域附近往往表现不佳，因为标准的回归损失会鼓励空间平均，从而模糊了锐利的边界。为解决这一问题，我们引入了一种混合专家框架，通过组合多个平滑的深度预测来处理深度边界处的不确定性。一个softmax加权头以逐像素的方式动态地在这些假设中进行选择。通过将我们的混合模型集成到预训练的最先进三维模型中，我们显著减少了边界伪影，并提升了整体重建精度。值得注意的是，我们的方法计算效率极高，即使在少量训练数据上进行微调也能带来泛化性的改进，同时仅引入可忽略的额外推理计算量，这为轻量且精确的三维重建指明了一个有前景的方向。