pixelSplat：从图像对生成3D高斯泼溅以实现可扩展的可泛化3D重建
pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction
AI总结：
pixelSplat提出从图像对学习3D高斯泼溅的前馈模型，通过可微概率采样克服局部极小值，在RealEstate10k和ACID上以2.5个数量级的渲染加速超越光场Transformer。
摘要：
我们提出pixelSplat，这是一个前馈模型，能够从图像对中学习重建由3D高斯基元参数化的3D辐射场。该模型具有实时且内存高效的渲染能力，既支持可扩展的训练，也能在推理时实现快速3D重建。为克服稀疏且局部支撑表示中固有的局部极小值问题，我们预测3D上的稠密概率分布，并从该概率分布中采样高斯均值。我们通过重参数化技巧使该采样操作可微，从而能够通过高斯泼溅表示反向传播梯度。我们在真实世界RealEstate10k和ACID数据集上的宽基线新视角合成任务中对方法进行了基准测试，结果优于最先进的光场Transformer，并将渲染速度提升了2.5个数量级，同时重建出可解释且可编辑的3D辐射场。
英文摘要：
We introduce pixelSplat, a feed-forward model that learns to reconstruct 3D radiance fields parameterized by 3D Gaussian primitives from pairs of images. Our model features real-time and memory-efficient rendering for scalable training as well as fast 3D reconstruction at inference time. To overcome local minima inherent to sparse and locally supported representations, we predict a dense probability distribution over 3D and sample Gaussian means from that probability distribution. We make this sampling operation differentiable via a reparameterization trick, allowing us to back-propagate gradients through the Gaussian splatting representation. We benchmark our method on wide-baseline novel view synthesis on the real-world RealEstate10k and ACID datasets, where we outperform state-of-the-art light field transformers and accelerate rendering by 2.5 orders of magnitude while reconstructing an interpretable and editable 3D radiance field.
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。
