Ensuring robustness in face recognition systems across various challenging
conditions is crucial for their versatility. State-of-the-art methods often
incorporate additional information, such as depth, thermal, or angular data, to
enhance performance. However, light field-based face recognition approaches
that leverage angular information face computational limitations. This paper
investigates the fundamental trade-off between spatio-angular resolution in
light field representation to achieve improved face recognition performance. By
utilizing macro-pixels with varying angular resolutions while maintaining the
overall image size, we aim to quantify the impact of angular information at the
expense of spatial resolution, while considering computational constraints. Our
experimental results demonstrate a notable performance improvement in face
recognition systems by increasing the angular resolution, up to a certain
extent, at the cost of spatial resolution.

光场表征中角度信息与空间角分辨率之间存在的权衡关系对人脸识别性能产生着显著的影响。本研究通过在保持整体图像大小的基础上利用具有不同角度分辨率的宏像素，以评估角度信息在空间分辨率降低的代价下对人脸识别性能的影响。实验结果表明，通过增加角度分辨率，可以在一定程度上显著提高人脸识别系统的性能。

面部识别中的空间分辨率与角度分辨率的权衡

Trade-off Between Spatial and Angular Resolution in Facial Recognition

Neural rendering has received tremendous attention since the advent of Neural
Radiance Fields (NeRF), and has pushed the state-of-the-art on novel-view
synthesis considerably. The recent focus has been on models that overfit to a
single scene, and the few attempts to learn models that can synthesize novel
views of unseen scenes mostly consist of combining deep convolutional features
with a NeRF-like model. We propose a different paradigm, where no deep features
and no NeRF-like volume rendering are needed. Our method is capable of
predicting the color of a target ray in a novel scene directly, just from a
collection of patches sampled from the scene. We first leverage epipolar
geometry to extract patches along the epipolar lines of each reference view.
Each patch is linearly projected into a 1D feature vector and a sequence of
transformers process the collection. For positional encoding, we parameterize
rays as in a light field representation, with the crucial difference that the
coordinates are canonicalized with respect to the target ray, which makes our
method independent of the reference frame and improves generalization. We show
that our approach outperforms the state-of-the-art on novel view synthesis of
unseen scenes even when being trained with considerably less data than prior
work.

该研究提出一种新的方法，利用极线几何法提取采样自场景的块，将其通过一系列变换器进行预处理后预测目标采样射线的颜色，从而在不需要深度特征和 NeRF-like 卷积体积渲染的情况下，实现对未见过的场景的新视图综合，其具有更好的泛化性能，并且即使使用比以前工作少得多的数据进行训练，也能胜过现有技术水平。