WildSplat：基于无位姿野外图像的前向高斯溅射方法
WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images
- State Key Lab of CAD&CG, Zhejiang University（浙江大学计算机辅助设计与图形学国家重点实验室）
- vivo BlueImage Lab（vivo蓝河图像实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对前向3D重建在光照变化场景下性能不佳的问题，提出双分支解耦架构的WildSplat框架，实现单步前向的野外新视角合成与外观编辑SOTA性能。
AI中文摘要：
尽管前向3D重建在高效新视角合成方面表现出色，但在面对光照变化的场景时通常会失效。为此，我们提出WildSplat，这是首个可针对无位姿野外图像实现外观条件化新视角合成的前向3D高斯溅射框架。为处理不一致的光度条件，我们提出一种双分支架构，将几何与外观显式解耦。几何分支提取不受外观影响的3D结构，同时预测相机位姿。为控制渲染外观，外观分支通过全局预调制交叉注意力机制将目标外观线索注入内容特征。为进一步避免特征纠缠，我们引入联合多参考训练策略以稳定训练过程。大量实验表明，WildSplat优于现有基于优化的方法和前向方法，仅需单次前向传播即可在稀疏输入的野外新视角合成与外观编辑任务中达到当前最优性能。
英文摘要：
While feedforward 3D reconstruction excels at efficient novel view synthesis, it typically falters when faced with scenes under varying illumination. To this end, we introduce WildSplat, the first feedforward 3D Gaussian Splatting framework capable of appearance-conditioned novel-view synthesis for unposed in-the-wild images. To handle inconsistent photometric conditions, we propose a dual-branch architecture that explicitly decouples geometry from appearance. The geometry branch extracts an appearance-invariant 3D structure and jointly predicts camera poses. To govern the rendering appearance, the appearance branch injects target appearance cues into the content features via a globally pre-modulated cross-attention mechanism. To further prevent feature entanglement, we introduce a joint multi-reference training strategy that stabilizes the training process. Extensive experiments show that WildSplat surpasses existing optimization-based and feedforward methods, achieving state-of-the-art performance in in-the-wild novel view synthesis and appearance editing from sparse inputs in a single forward pass.
