论文标题
PDRF：从模糊图像中逐渐消除了快速，强大的场景重建场景的辐射场
PDRF: Progressively Deblurring Radiance Field for Fast and Robust Scene Reconstruction from Blurry Images
论文作者
论文摘要
我们提出了逐渐变化的辐射场（PDRF），这是一种从模糊图像中有效重建高质量辐射场的新方法。尽管当前最新的（SOTA）场景重建方法实现了照片真实的渲染，因此清洁源视图会导致其表演，而当源视图受Blur的影响时，它们通常会观察到野外图像。以前的脱毛方法要么不解释3D几何形状，要么在计算上是强烈的。为了解决这些问题，PDRF是Radiance Field建模中逐渐消除的方案，通过合并3D场景上下文来准确地模拟模糊。 PDRF进一步使用了有效的重要性采样方案，从而导致快速场景优化。具体而言，PDRF提出了一个粗射线渲染器，以快速估计体素密度和特征。然后，使用细素渲染器来实现高质量的射线追踪。我们进行了广泛的实验，并表明PDRF比以前的SOTA快15倍，同时在合成场景和真实场景上都能取得更好的性能。
We present Progressively Deblurring Radiance Field (PDRF), a novel approach to efficiently reconstruct high quality radiance fields from blurry images. While current State-of-The-Art (SoTA) scene reconstruction methods achieve photo-realistic rendering results from clean source views, their performances suffer when the source views are affected by blur, which is commonly observed for images in the wild. Previous deblurring methods either do not account for 3D geometry, or are computationally intense. To addresses these issues, PDRF, a progressively deblurring scheme in radiance field modeling, accurately models blur by incorporating 3D scene context. PDRF further uses an efficient importance sampling scheme, which results in fast scene optimization. Specifically, PDRF proposes a Coarse Ray Renderer to quickly estimate voxel density and feature; a Fine Voxel Renderer is then used to achieve high quality ray tracing. We perform extensive experiments and show that PDRF is 15X faster than previous SoTA while achieving better performance on both synthetic and real scenes.
