Learning Spatial Attention for Face Super-Resolution, C. Super-resolving Tiny Faces with Face Feature Vectors, Y. Implicit Subspace Prior Learning for Dual-Blind Face Restoration, L. Chen et al., CRC 2020.Ī Densely Connected Face Super-Resolution Network Based on Attention Mechanism, Y. Wang et al., Neurocomputing 2020.Įfficient Face Super-Resolution Based on Separable Convolution Projection Networks, X. RBPNET: An asymptotic Residual Back-Projection Network for super-resolution of very low-resolution face image, X. Face hallucination from low quality images using definition-scalable inference, X. Zheng et al., ICIP 2019.ĪTMFN: Adaptive-threshold-based Multi-model Fusion Network for Compressed Face Hallucination, K. Guided Cyclegan Via Semi-Dual Optimal Transport for Photo-Realistic Face Super-Resolution, W. chen et al., TCYB 2019.įace Image Super-Resolution Using Inception Residual Network and GAN Framework, S. Sequential Gating Ensemble Network for Noise Robust Multiscale Face Restoration, Z. Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement, Yibing Song et al. Nie et al., ICTAI 2018.įace Hallucination by Attentive Sequence Optimization with Reinforcement Learning, Yukai Shi et al. Han et al., ICME 2018įace Hallucination via Convolution Neural Network, H. Huang et al., AISC 2018.Ī Noise Robust Face Hallucination Framework Via Cascaded Model of Deep Convolutional Networks and Manifold Learning, L. Super-resolution Reconstruction of Face Image Based on Convolution Network, W. Attention-Aware Face Hallucination via Deep Reinforcement Learning, Q. Wavelet-SRNet: A Wavelet-Based CNN for Multi-Scale Face Super Resolution, H. High-Quality Face Image SR Using Conditional Generative Adversarial Networks, B. ![]() Lu et al., ICIP 2017.įace Super-Resolution Through Wasserstein GANs. Feng et at., ICPR 2016.įace hallucination using region-based deep convolutional networks, T. Ko et al., ICME 2016.įace hallucination by deep traversal network, Z. Patch-based face hallucination with multitask deep neural network, W. Global-local fusion network for face super-resolution, Tao Lu et al., Neurocomputing 2020. Global-Local Face Upsampling Network, O. Face Hallucination Using Convolutional Neural Network with Iterative Back Projection, D. Ultra-resolving face images by discriminative generative networks, X. Learning Face Hallucination in the Wild, E. Huang et al., PR 2010.ĭeep learning-based Methods General FSR Methods Super-resolution of human face image using canonical correlation analysis, H. Hallucinating faces: LPH super-resolution and neighbor reconstruction for residue compensation, Y. Abbasi et al., Ī two-step approach to hallucinating faces: global parametric model and local nonparametric model, C. Identity-Preserving Pose-Robust Face Hallucination Through Face Subspace Prior, A. Liu et al., ECCV 2012.Ī convex approach for image hallucination, P. Ī Bayesian Approach to Alignment-Based Image Hallucination, C. Super-resolution of face images using kernel PCA-based prior, A. Hallucinating face by eigentransformation, X. Hallucinating Color Face Image by Learning Graph Representation in Quaternion Space, L. Liu et al., INS 2020.įace hallucination via multiple feature learning with hierarchical structure, L. Robust face hallucination via locality-constrained multiscale coding, L. SSR2: Sparse signal recovery for single-image super-resolution on faces with extreme low resolutions, R. Robust Face Image Super-Resolution via Joint Learning of Subdivided Contextual Model, L. įace Hallucination via Coarse-to-Fine Recursive Kernel Regression Structure, J. ![]() Context-Patch based Face Hallucination via Thresholding Locality-Constrained Representation and Reproducing Learning, J. Hallucinating Face Image by Regularization Models in High-Resolution Feature Space, J. įace Hallucination Using Linear Models of Coupled Sparse Support, R. Multilayer Locality-Constrained Iterative Neighbor Embedding, J. Noise robust face hallucination via locality-constrained representation, J. Position-patch based face hallucination using convex optimization, C. Hallucinating face by position-patch, Ma et al., PR 2010. Super-resolution through neighbor embedding, Chang et al. Classical Methods Classical Patch-based Methods We thank the authors for sharing their codes. The eval_psnr_ssim.py and calc_lpips.py are built on and. Note that the partition of the dataset follows. *As for deep learning-based methods, we provide the training sets, and the experimental results of several state-of-the-art methods in (va2i) and. *Some classical algorithms (including NE, LSR, SR, LcR, LINE, TLcR-RL, and EigTran) implemented by myself can be found here. Learning-based Face Super-resolution: A Survey},Īuthor=,
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |