VolRecon：基于有符号射线距离函数的体绘制用于可泛化的多视图重建
VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction
AI总结：
VolRecon提出一种基于Signed Ray Distance Function的可泛化多视图隐式重建方法，结合多视图投影特征与粗略全局体积特征，利用射线Transformer渲染颜色和深度，在DTU和ETH3D数据集上表现优异。
摘要：
Neural Radiance Fields (NeRF)在新视图合成方面的成功启发了研究人员提出神经隐式场景重建。然而，大多数现有的神经隐式重建方法优化的是每个场景的参数，因此缺乏对新场景的泛化能力。我们引入了VolRecon，一种使用Signed Ray Distance Function (SRDF)的新型可泛化隐式重建方法。为了重建具有精细细节和低噪声的场景，VolRecon结合了从多视图特征聚合的投影特征，以及从粗略全局特征体积中插值的体积特征。使用射线Transformer，我们计算射线上采样点的SRDF值，然后渲染颜色和深度。在DTU数据集上，VolRecon在稀疏视图重建中比SparseNeuS高出约30%，在全视图重建中达到了与MVSNet相当的精度。此外，我们的方法在大规模ETH3D基准上表现出良好的泛化性能。
英文摘要：
The success of the Neural Radiance Fields (NeRF) in novel view synthesis has inspired researchers to propose neural implicit scene reconstruction. However, most existing neural implicit reconstruction methods optimize per-scene parameters and therefore lack generalizability to new scenes. We introduce VolRecon, a novel generalizable implicit reconstruction method with Signed Ray Distance Function (SRDF). To reconstruct the scene with fine details and little noise, VolRecon combines projection features aggregated from multi-view features, and volume features interpolated from a coarse global feature volume. Using a ray transformer, we compute SRDF values of sampled points on a ray and then render color and depth. On DTU dataset, VolRecon outperforms SparseNeuS by about 30% in sparse view reconstruction and achieves comparable accuracy as MVSNet in full view reconstruction. Furthermore, our approach exhibits good generalization performance on the large-scale ETH3D benchmark.
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。
