IDESplat：面向可泛化三维高斯泼溅的迭代深度概率估计
IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splatting
提出迭代深度概率提升单元（DPBU），通过级联 warp 的极线注意力乘法融合来精化深度候选，可直接用于提升前馈式高斯泼溅的深度估计精度与泛化性。
原文依据 we introduce a Depth Probability Boosting Unit (DPBU) that integrates epipolar attention maps produced by cascading warp operations in a multiplicative manner
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论可泛化三维高斯泼溅旨在利用前馈网络直接预测高斯参数以进行场景重建。在这些参数中，高斯均值尤其难以预测，因此通常先估计深度，再反投影以获得高斯球中心。现有方法通常仅依赖单次 warp 来估计深度概率，这阻碍了它们充分利用跨视角几何线索的能力，导致深度图不可靠且粗糙。为解决这一局限，我们提出 IDESplat，它迭代地应用 warp 操作以提升深度概率估计，从而实现准确的高斯均值预测。首先，为消除单次 warp 固有的不可靠性，我们引入深度概率提升单元（DPBU），它以乘法方式整合由级联 warp 操作产生的极线注意力图。接着，我们通过堆叠多个 DPBU 构建迭代深度估计过程，逐步识别具有高似然性的潜在深度候选。随着 IDESplat 迭代地提升深度概率估计并更新深度候选，深度图逐渐细化，从而获得准确的高斯均值。我们在 RealEstate10K、ACID 和 DL3DV 上进行了实验。IDESplat 实现了出色的重建质量和最优性能，并具有实时效率。在 RE10K 上，它比 DepthSplat 的峰值信噪比高 0.33 dB，仅使用 10.7% 的参数和 70% 的内存。此外，在跨数据集实验中，我们的 IDESplat 在 DTU 数据集上比 DepthSplat 的峰值信噪比提高了 2.95 dB，展示了其强大的泛化能力。
英文原文摘要 1686 字符
Generalizable 3D Gaussian Splatting aims to directly predict Gaussian parameters using a feed-forward network for scene reconstruction. Among these parameters, Gaussian means are particularly difficult to predict, so depth is usually estimated first and then unprojected to obtain the Gaussian sphere centers. Existing methods typically rely solely on a single warp to estimate depth probability, which hinders their ability to fully leverage cross-view geometric cues, resulting in unreliable and coarse depth maps. To address this limitation, we propose IDESplat, which iteratively applies warp operations to boost depth probability estimation for accurate Gaussian mean prediction. First, to eliminate the inherent unreliability of a single warp, we introduce a Depth Probability Boosting Unit (DPBU) that integrates epipolar attention maps produced by cascading warp operations in a multiplicative manner. Next, we construct an iterative depth estimation process by stacking multiple DPBUs, progressively identifying potential depth candidates with high likelihood. As IDESplat iteratively boosts depth probability estimates and updates the depth candidates, the depth map is gradually refined, resulting in accurate Gaussian means. We conduct experiments on RealEstate10K, ACID and DL3DV. IDESplat achieves outstanding reconstruction quality and state-of-the-art performance with real-time efficiency. On RE10K, it outperforms DepthSplat by 0.33 dB in PSNR, using only 10.7% of the parameters and 70% of the memory. Additionally, our IDESplat improves PSNR by 2.95 dB over DepthSplat on the DTU dataset in cross-dataset experiments, demonstrating its strong generalization ability.