A large number of 3D spectral descriptors have been proposed in the literature, which act as an essential component for 3D deformable shape matching and related applications. An outstanding descriptor should have desirable natures including high-level descriptive capacity, cheap storage, and robustness to a set of nuisances. It is, however, unclear which descriptors are more suitable for a particular application. This paper fills the gap by comprehensively evaluating nine state-of-the-art spectral descriptors on ten popular deformable shape datasets as well as perturbations such as mesh discretization, geometric noise, scale transformation, non-isometric setting, partiality, and topological noise. Our evaluated terms for a spectral descriptor cover four major concerns, i.e., distinctiveness, robustness, compactness, and computational efficiency. In the end, we present a summary of the overall performance and several interesting findings that can serve as guidance for the following researchers to construct a new spectral descriptor and choose an appropriate spectral feature in a particular application.

Blind face restoration (BFR) from severely degraded face images is important in face image processing, and has attracted increasing attention due to its wide applications. How-ever, due to the complex unknown degradations in real-world scenarios, existing priors-based methods tend to restore faces with unstable quality. In this paper, we propose a Facial Landmarks and Generative Priors Guided Blind Face Restoration Network (FGPNet) to seamlessly integrate the advantages of generative priors and face-specific geometry priors. Specifically, we pretrain a high-quality (HQ) face synthesis generative adversarial network (GAN) and a landmarks prediction network, and then embed them into a U-shaped deep neural network (DNN) as decoder priors to guide face restoration, during which the generative priors can provide adequate details and the landmarks priors provide geometry and semantic information. Furthermore, we design facial priors fusion (FPF) blocks to incorporate the prior features from pretrained face synthesis GAN and landmarks prediction network in an adaptive and progressive manner, making our FGPNet exhibits good generalization in real-world application. Experiments demonstrate the superiority of our FGPNet in comparison to state-of-the-arts, and also show its potential in handling real-world low-quality images from several practical applications.