SmileSplat：面向无约束稀疏图像的可泛化高斯溅射
SmileSplat: Generalizable Gaussian Splats for Unconstrained Sparse Images
AI总结：
针对无需真实相机参数的无约束稀疏多视图图像场景，提出可泛化高斯溅射方法SmileSplat，通过多头高斯回归解码器和Bundle-Adjusting模块优化高斯表面元素与相机参数，在新视图渲染等任务上实现SOTA性能。
摘要：
稀疏多视图图像可通过可泛化高斯溅射方法学习预测显式辐射场，当无需将真实相机参数作为输入时，这类方法在现实生活中具有更广泛的应用前景。本文提出一种新颖的可泛化高斯溅射方法SmileSplat，仅需无约束稀疏多视图图像即可为多样场景重建像素对齐的高斯表面元素。首先，基于多头高斯回归解码器预测高斯表面元素，其自由度更低但多视图一致性更优；此外，利用高质量法向先验增强高斯表面元素的法向量。其次，基于提出的Bundle-Adjusting Gaussian Splatting模块优化高斯表面元素与相机参数（内参和外参），以获得高质量高斯辐射场用于新视图合成任务。在公开数据集上针对新视图渲染和深度图预测任务开展大量实验，结果表明所提方法在多种3D视觉任务中达到最先进性能。更多信息可访问项目页面（https://yanyan-li.github.io/project/gs/smilesplat）。
英文摘要：
Sparse Multi-view Images can be Learned to predict explicit radiance fields via Generalizable Gaussian Splatting approaches, which can achieve wider application prospects in real-life when ground-truth camera parameters are not required as inputs. In this paper, a novel generalizable Gaussian Splatting method, SmileSplat, is proposed to reconstruct pixel-aligned Gaussian surfels for diverse scenarios only requiring unconstrained sparse multi-view images. First, Gaussian surfels are predicted based on the multi-head Gaussian regression decoder, which can are represented with less degree-of-freedom but have better multi-view consistency. Furthermore, the normal vectors of Gaussian surfel are enhanced based on high-quality of normal priors. Second, the Gaussians and camera parameters (both extrinsic and intrinsic) are optimized to obtain high-quality Gaussian radiance fields for novel view synthesis tasks based on the proposed Bundle-Adjusting Gaussian Splatting module. Extensive experiments on novel view rendering and depth map prediction tasks are conducted on public datasets, demonstrating that the proposed method achieves state-of-the-art performance in various 3D vision tasks. More information can be found on our project page (https://yanyan-li.github.io/project/gs/smilesplat)
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。
