用深度去模糊网络加速辐射场重建，训练更快画质更好
Exploiting Deblurring Networks for Radiance Fields
- 用神经网络先去模糊，再构建辐射场，交替优化提升质量
- 在运动模糊和散焦模糊下均实现顶尖画质，训练时间大幅缩短
- 支持体素和3D高斯等多种场景表示，适合视觉重建研究者
本文提出DeepDeblurRF，一种新颖的辐射场去模糊方法，可从模糊的训练视图中高效合成高质量新视角，显著降低训练时间。该方法利用基于深度神经网络（DNN）的去模糊模块，兼具出色的去模糊性能与计算效率。为有效融合DNN去模糊与辐射场构建，提出一种辐射场（RF）引导的去模糊机制，并设计交替进行去模糊与辐射场构建的迭代框架。此外，DeepDeblurRF兼容多种场景表示，如体素网格和3D高斯，拓展了应用范围。我们还构建了首个大规模合成数据集BlurRF-Synth，用于训练辐射场去模糊模型。在相机运动模糊和散焦模糊场景下的大量实验表明，DeepDeblurRF在新视角合成质量上达到当前最优水平，且训练时间显著减少。
原文摘要 · Abstract (English)
In this paper, we propose DeepDeblurRF, a novel radiance field deblurring approach that can synthesize high-quality novel views from blurred training views with significantly reduced training time. DeepDeblurRF leverages deep neural network (DNN)-based deblurring modules to enjoy their deblurring performance and computational efficiency. To effectively combine DNN-based deblurring and radiance field construction, we propose a novel radiance field (RF)-guided deblurring and an iterative framework that performs RF-guided deblurring and radiance field construction in an alternating manner. Moreover, DeepDeblurRF is compatible with various scene representations, such as voxel grids and 3D Gaussians, expanding its applicability. We also present BlurRF-Synth, the first large-scale synthetic dataset for training radiance field deblurring frameworks. We conduct extensive experiments on both camera motion blur and defocus blur, demonstrating that DeepDeblurRF achieves state-of-the-art novel-view synthesis quality with significantly reduced training time.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。