اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدLearning the Loss Functions in a Discriminative Space for Video Restoration
313
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
With more advanced deep network architectures and learning schemes such as GANs, the performance of video restoration algorithms has greatly improved recently. Meanwhile, the loss functions for optimizing deep neural networks remain relatively unchanged. To this end, we propose a new framework for building effective loss functions by learning a discriminative space specific to a video restoration task. Our framework is similar to GANs in that we iteratively train two networks - a generator and a loss network. The generator learns to restore videos in a supervised fashion, by following ground truth features through the feature matching in the discriminative space learned by the loss network. In addition, we also introduce a new relation loss in order to maintain the temporal consistency in output videos. Experiments on video superresolution and deblurring show that our method generates visually more pleasing videos with better quantitative perceptual metric values than the other state-of-the-art methods.
قيم البحث
اقرأ أيضاً
Liquify is a common technique for image editing, which can be used for image distortion. Due to the uncertainty in the distortion variation, restoring distorted images caused by liquify filter is a challenging task. To edit images in an efficient way
, distorted images are expected to be restored automatically. This paper aims at the distorted image restoration, which is characterized by seeking the appropriate warping and completion of a distorted image. Existing methods focus on the hardware assistance or the geometric principle to solve the specific regular deformation caused by natural phenomena, but they cannot handle the irregularity and uncertainty of artificial distortion in this task. To address this issue, we propose a novel generative and discriminative learning method based on deep neural networks, which can learn various reconstruction mappings and represent complex and high-dimensional data. This method decomposes the task into a rectification stage and a refinement stage. The first stage generative network predicts the mapping from the distorted images to the rectified ones. The second stage generative network then further optimizes the perceptual quality. Since there is no available dataset or benchmark to explore this task, we create a Distorted Face Dataset (DFD) by forward distortion mapping based on CelebA dataset. Extensive experimental evaluation on the proposed benchmark and the application demonstrates that our method is an effective way for distorted image restoration.
Recently, much progress has been made in unsupervised restoration learning. However, existing methods more or less rely on some assumptions on the signal and/or degradation model, which limits their practical performance. How to construct an optimal
criterion for unsupervised restoration learning without any prior knowledge on the degradation model is still an open question. Toward answering this question, this work proposes a criterion for unsupervised restoration learning based on the optimal transport theory. This criterion has favorable properties, e.g., approximately maximal preservation of the information of the signal, whilst achieving perceptual reconstruction. Furthermore, though a relaxed unconstrained formulation is used in practical implementation, we show that the relaxed formulation in theory has the same solution as the original constrained formulation. Experiments on synthetic and real-world data, including realistic photographic, microscopy, depth, and raw depth images, demonstrate that the proposed method even compares favorably with supervised methods, e.g., approaching the PSNR of supervised methods while having better perceptual quality. Particularly, for spatially correlated noise and realistic microscopy images, the proposed method not only achieves better perceptual quality but also has higher PSNR than supervised methods. Besides, it shows remarkable superiority in harsh practical conditions with complex noise, e.g., raw depth images.
Purpose: To improve reconstruction fidelity of fine structures and textures in deep learning (DL) based reconstructions. Methods: A novel patch-based Unsupervised Feature Loss (UFLoss) is proposed and incorporated into the training of DL-based reco
nstruction frameworks in order to preserve perceptual similarity and high-order statistics. The UFLoss provides instance-level discrimination by mapping similar instances to similar low-dimensional feature vectors and is trained without any human annotation. By adding an additional loss function on the low-dimensional feature space during training, the reconstruction frameworks from under-sampled or corrupted data can reproduce more realistic images that are closer to the original with finer textures, sharper edges, and improved overall image quality. The performance of the proposed UFLoss is demonstrated on unrolled networks for accelerated 2D and 3D knee MRI reconstruction with retrospective under-sampling. Quantitative metrics including NRMSE, SSIM, and our proposed UFLoss were used to evaluate the performance of the proposed method and compare it with others. Results: In-vivo experiments indicate that adding the UFLoss encourages sharper edges and more faithful contrasts compared to traditional and learning-based methods with pure l2 loss. More detailed textures can be seen in both 2D and 3D knee MR images. Quantitative results indicate that reconstruction with UFLoss can provide comparable NRMSE and a higher SSIM while achieving a much lower UFLoss value. Conclusion: We present UFLoss, a patch-based unsupervised learned feature loss, which allows the training of DL-based reconstruction to obtain more detailed texture, finer features, and sharper edges with higher overall image quality under DL-based reconstruction frameworks.
We propose discriminative adversarial networks (DAN) for semi-supervised learning and loss function learning. Our DAN approach builds upon generative adversarial networks (GANs) and conditional GANs but includes the key differentiator of using two di
scriminators instead of a generator and a discriminator. DAN can be seen as a framework to learn loss functions for predictors that also implements semi-supervised learning in a straightforward manner. We propose instantiations of DAN for two different prediction tasks: classification and ranking. Our experimental results on three datasets of different tasks demonstrate that DAN is a promising framework for both semi-supervised learning and learning loss functions for predictors. For all tasks, the semi-supervised capability of DAN can significantly boost the predictor performance for small labeled sets with minor architecture changes across tasks. Moreover, the loss functions automatically learned by DANs are very competitive and usually outperform the standard pairwise and negative log-likelihood loss functions for both semi-supervised and supervised learning.
Learning based video compression attracts increasing attention in the past few years. The previous hybrid coding approaches rely on pixel space operations to reduce spatial and temporal redundancy, which may suffer from inaccurate motion estimation o
r less effective motion compensation. In this work, we propose a feature-space video coding network (FVC) by performing all major operations (i.e., motion estimation, motion compression, motion compensation and residual compression) in the feature space. Specifically, in the proposed deformable compensation module, we first apply motion estimation in the feature space to produce motion information (i.e., the offset maps), which will be compressed by using the auto-encoder style network. Then we perform motion compensation by using deformable convolution and generate the predicted feature. After that, we compress the residual feature between the feature from the current frame and the predicted feature from our deformable compensation module. For better frame reconstruction, the reference features from multiple previous reconstructed frames are also fused by using the non-local attention mechanism in the multi-frame feature fusion module. Comprehensive experimental results demonstrate that the proposed framework achieves the state-of-the-art performance on four benchmark datasets including HEVC, UVG, VTL and MCL-JCV.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
