论文标题
NERF ++：分析和改善神经辐射场
NeRF++: Analyzing and Improving Neural Radiance Fields
论文作者
论文摘要
神经辐射场（NERF）为各种捕获设置获得了令人印象深刻的视图综合结果，包括对有限场景的360个捕获以及对有限和无限场景的前向捕获。 NERF拟合多层感知器（MLP），代表视图不透明度和视图依赖性颜色量与一组训练图像，并根据体积渲染技术采样新视图。在这份技术报告中，我们首先评论了辐射领域及其潜在的歧义，即形状范围的歧义，并分析了Nerf在避免这种歧义方面的成功。其次，我们解决了将NERF应用于大规模无界3D场景中的360个对象捕获的参数化问题。在这种挑战的情况下，我们的方法改善了综合保真度。代码可在https://github.com/kai-46/nerfplusplus上找到。
Neural Radiance Fields (NeRF) achieve impressive view synthesis results for a variety of capture settings, including 360 capture of bounded scenes and forward-facing capture of bounded and unbounded scenes. NeRF fits multi-layer perceptrons (MLPs) representing view-invariant opacity and view-dependent color volumes to a set of training images, and samples novel views based on volume rendering techniques. In this technical report, we first remark on radiance fields and their potential ambiguities, namely the shape-radiance ambiguity, and analyze NeRF's success in avoiding such ambiguities. Second, we address a parametrization issue involved in applying NeRF to 360 captures of objects within large-scale, unbounded 3D scenes. Our method improves view synthesis fidelity in this challenging scenario. Code is available at https://github.com/Kai-46/nerfplusplus.
