迈向通用化 NeRF 中的退化鲁棒重建
Towards Degradation-Robust Reconstruction in Generalizable NeRF
AI总结：
本文针对通用化 NeRF 在图像退化下鲁棒性研究不足的问题，构建了包含 5 万张图像的 Objaverse Blur Dataset，并提出一种模型无关的 3D 感知特征提取模块，有效提升了 GNeRF 在多种退化条件下的重建质量。
摘要：
跨场景的通用化神经辐射场（GNeRF）已被证明是通过使用源图像的深度图像特征来表示场景，从而避免逐场景优化的有效方法。然而，尽管其在现实世界应用中具有潜力，但关于 GNeRF 对源图像中存在的不同类型退化的鲁棒性的研究仍然有限。缺乏此类研究主要归因于缺乏适合训练退化鲁棒的通用化 NeRF 模型的大规模数据集。为了填补这一空白并促进对 3D 重建任务退化鲁棒性的研究，我们构建了 Objaverse Blur Dataset，包含来自超过 1000 个设置的 50,000 张图像，具有多个级别的模糊退化。此外，我们设计了一个简单且模型无关的模块，用于增强 GNeRF 的退化鲁棒性。具体而言，通过轻量级深度估计器和去噪器提取 3D 感知特征，所提出的模块在不同的退化类型和级别下，在定量和视觉质量方面均显示出对 GNeRF 中不同流行方法的改进。我们的数据集和代码将公开发布。
英文摘要：
Generalizable Neural Radiance Field (GNeRF) across scenes has been proven to be an effective way to avoid per-scene optimization by representing a scene with deep image features of source images. However, despite its potential for real-world applications, there has been limited research on the robustness of GNeRFs to different types of degradation present in the source images. The lack of such research is primarily attributed to the absence of a large-scale dataset fit for training a degradation-robust generalizable NeRF model. To address this gap and facilitate investigations into the degradation robustness of 3D reconstruction tasks, we construct the Objaverse Blur Dataset, comprising 50,000 images from over 1000 settings featuring multiple levels of blur degradation. In addition, we design a simple and model-agnostic module for enhancing the degradation robustness of GNeRFs. Specifically, by extracting 3D-aware features through a lightweight depth estimator and denoiser, the proposed module shows improvement on different popular methods in GNeRFs in terms of both quantitative and visual quality over varying degradation types and levels. Our dataset and code will be made publicly available.
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。
