论文标题
WILDNERF：使用稀疏单眼数据捕获的野外动态场景的完整查看合成
wildNeRF: Complete view synthesis of in-the-wild dynamic scenes captured using sparse monocular data
论文作者
论文摘要
我们提出了一种新颖的神经辐射模型，该模型可在自我监督的方式中训练，以构成动态非结构化场景的新型视图综合。我们的端到端可训练算法在几秒钟内学习了高度复杂，现实世界中的静态场景，并在几分钟内具有刚性和非刚性运动。通过区分静态和运动以运动为中心的像素，我们从一组稀疏的图像组中创建高质量的表示。我们对现有基准进行了广泛的定性和定量评估，并在具有挑战性的NVIDIA动态场景数据集上为性能度量设定了最先进的评估。此外，我们评估了我们在挑战现实数据集（例如cholec80 and Surgicalactions160）上的模型性能。
We present a novel neural radiance model that is trainable in a self-supervised manner for novel-view synthesis of dynamic unstructured scenes. Our end-to-end trainable algorithm learns highly complex, real-world static scenes within seconds and dynamic scenes with both rigid and non-rigid motion within minutes. By differentiating between static and motion-centric pixels, we create high-quality representations from a sparse set of images. We perform extensive qualitative and quantitative evaluation on existing benchmarks and set the state-of-the-art on performance measures on the challenging NVIDIA Dynamic Scenes Dataset. Additionally, we evaluate our model performance on challenging real-world datasets such as Cholec80 and SurgicalActions160.
