We introduce IFFNeRF to estimate the six degrees-of-freedom (6DoF) camera
pose of a given image, building on the Neural Radiance Fields (NeRF)
formulation. IFFNeRF is specifically designed to operate in real-time and
eliminates the need for an initial pose guess that is proximate to the sought
solution. IFFNeRF utilizes the Metropolis-Hasting algorithm to sample surface
points from within the NeRF model. From these sampled points, we cast rays and
deduce the color for each ray through pixel-level view synthesis. The camera
pose can then be estimated as the solution to a Least Squares problem by
selecting correspondences between the query image and the resulting bundle. We
facilitate this process through a learned attention mechanism, bridging the
query image embedding with the embedding of parameterized rays, thereby
matching rays pertinent to the image. Through synthetic and real evaluation
settings, we show that our method can improve the angular and translation error
accuracy by 80.1% and 67.3%, respectively, compared to iNeRF while performing
at 34fps on consumer hardware and not requiring the initial pose guess.

我们介绍了 IFFNeRF 以估计给定图像的六自由度（6DoF）相机姿态，基于神经辐射场（NeRF）的形成。IFFNeRF 专门设计用于实时操作，并消除了需要靠近所需解的初始姿态猜测的需求。IFFNeRF 利用 Metroplis-Hasting 算法从 NeRF 模型中采样表面点。通过对这些采样点投射射线并通过像素级视图合成来推断每个射线的颜色。然后，通过在查询图像和结果束之间选择对应关系来估计相机姿态作为最小二乘问题的解。我们通过学习的注意机制促进这个过程，将查询图像嵌入与参数化射线的嵌入进行匹配，从而与图像相关的射线相匹配。通过合成和实际评估环境，我们表明我们的方法相对于 iNeRF 可以提高 80.1％的角度和 67.3％的平移误差准确性，同时在消费硬件上以 34fps 运行并且不需要初始姿态猜测。