SPFSplatV2: 基于稀疏视图的高效自监督无姿态3D高斯泼溅
SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
AI总结：
提出SPFSplatV2，一种从稀疏多视图图像进行3D高斯泼溅的前馈框架，无需真实姿态，通过共享特征提取、掩码注意力机制和重投影损失实现高效姿态估计和新视图合成，在域内外均达到最先进性能。
摘要：
我们介绍SPFSplatV2，一种高效的前馈框架，用于从稀疏多视图图像进行3D高斯泼溅，在训练或推理时无需真实姿态。该框架采用共享特征提取骨干网络，从无姿态输入中联合预测规范空间中的3D高斯基元和相机姿态。为了实现高效准确的姿态估计，我们引入了目标视图姿态预测的掩码注意力机制和重投影损失，强制像素对齐的高斯基元，提供更强的几何约束。我们进一步展示了我们的训练框架与不同重建架构的兼容性，产生了两种模型变体。值得注意的是，尽管没有姿态监督，我们的方法在域内和域外的新视图合成中均达到了最先进性能，即使在极端视角变化和有限图像重叠的情况下也是如此。在相对姿态估计方面，它也超越了许多依赖几何监督的方法。通过消除对真实姿态的依赖，我们的方法具有可扩展性，可以利用更大、更多样化的数据集。代码和预训练模型将在我们的项目页面上提供：此 https URL。
英文摘要：
We introduce SPFSplatV2, an efficient feed-forward framework for 3D Gaussian splatting from sparse multi-view images, requiring no ground-truth poses during training or inference. The framework employs a shared feature extraction backbone to jointly predict 3D Gaussian primitives and camera poses in a canonical space from unposed inputs. To enable efficient and accurate pose estimation, we introduce a masked attention mechanism for target-view pose prediction and a reprojection loss that enforces pixel-aligned Gaussian primitives, providing stronger geometric constraints. We further demonstrate the compatibility of our training framework with different reconstruction architectures, resulting in two model variants. Remarkably, despite the absence of pose supervision, our method achieves state-of-the-art performance in both in-domain and out-of-domain novel view synthesis, even under extreme viewpoint changes and limited image overlap. It also surpasses many methods that rely on geometric supervision in relative pose estimation. By eliminating dependence on ground-truth poses, our method offers the scalability to leverage larger and more diverse datasets. Code and pretrained models will be available on our project page: https://ranrhuang.github.io/spfsplatv2/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
