PyTorchKR Papers

최신 논문

총 1,320편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2106.10437공식 코드 · Papers with Code

One-to-many Approach for Improving Super-Resolution

Recently, there has been discussions on the ill-posed nature of super-resolution that multiple possible reconstructions exist for a given low-resolution image. Using normalizing flows, SRflow[23] achieves state-of-the-art perceptual quality by learning the distribution of the output instead of a deterministic output to one estimate. In this paper, we adapt the concepts of SRFlow to improve GAN-based super-resolution by properly implementing the one-to-many property. We modify the generator to estimate a distribution as a mapping from random noise. We improve the content loss that hampers the perceptual training objectives. We also propose additional training techniques to further enhance the perceptual quality of generated images. Using our proposed methods, we were able to improve the performance of ESRGAN[1] in x4 perceptual SR and achieve the state-of-the-art LPIPS score in x16 perceptual extreme SR by applying our methods to RFB-ESRGAN[21].

arXiv:2106.08762공식 코드 · Papers with Code

Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects

We address the novel task of jointly reconstructing the 3D shape, texture, and motion of an object from a single motion-blurred image. While previous approaches address the deblurring problem only in the 2D image domain, our proposed rigorous modeling of all object properties in the 3D domain enables the correct description of arbitrary object motion. This leads to significantly better image decomposition and sharper deblurring results. We model the observed appearance of a motion-blurred object as a combination of the background and a 3D object with constant translation and rotation. Our method minimizes a loss on reconstructing the input image via differentiable rendering with suitable regularizers. This enables estimating the textured 3D mesh of the blurred object with high fidelity. Our method substantially outperforms competing approaches on several benchmarks for fast moving objects deblurring. Qualitative results show that the reconstructed 3D mesh generates high-quality temporal super-resolution and novel views of the deblurred object.

arXiv:2106.07066공식 코드 · Papers with Code

Enhanced Hyperspectral Image Super-Resolution via RGB Fusion and TV-TV Minimization

Hyperspectral (HS) images contain detailed spectral information that has proven crucial in applications like remote sensing, surveillance, and astronomy. However, because of hardware limitations of HS cameras, the captured images have low spatial resolution. To improve them, the low-resolution hyperspectral images are fused with conventional high-resolution RGB images via a technique known as fusion based HS image super-resolution. Currently, the best performance in this task is achieved by deep learning (DL) methods. Such methods, however, cannot guarantee that the input measurements are satisfied in the recovered image, since the learned parameters by the network are applied to every test image. Conversely, model-based algorithms can typically guarantee such measurement consistency. Inspired by these observations, we propose a framework that integrates learning and model based methods. Experimental results show that our method produces images of superior spatial and spectral resolution compared to the current leading methods, whether model- or DL-based.

arXiv:2106.06847공식 코드 · Papers with Code

Video Super-Resolution Transformer

Video super-resolution (VSR), with the aim to restore a high-resolution video from its corresponding low-resolution version, is a spatial-temporal sequence prediction problem. Recently, Transformer has been gaining popularity due to its parallel computing ability for sequence-to-sequence modeling. Thus, it seems to be straightforward to apply the vision Transformer to solve VSR. However, the typical block design of Transformer with a fully connected self-attention layer and a token-wise feed-forward layer does not fit well for VSR due to the following two reasons. First, the fully connected self-attention layer neglects to exploit the data locality because this layer relies on linear layers to compute attention maps. Second, the token-wise feed-forward layer lacks the feature alignment which is important for VSR since this layer independently processes each of the input token embeddings without any interaction among them. In this paper, we make the first attempt to adapt Transformer for VSR. Specifically, to tackle the first issue, we present a spatial-temporal convolutional self-attention layer with a theoretical understanding to exploit the locality information. For the second issue, we design a bidirectional optical flow-based feed-forward layer to discover the correlations across different video frames and also align features. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our proposed method. The code will be available at https://github.com/caojiezhang/VSR-Transformer.

arXiv:2106.06742공식 코드 · Papers with Code

Task Transformer Network for Joint MRI Reconstruction and Super-Resolution

The core problem of Magnetic Resonance Imaging (MRI) is the trade off between acceleration and image quality. Image reconstruction and super-resolution are two crucial techniques in Magnetic Resonance Imaging (MRI). Current methods are designed to perform these tasks separately, ignoring the correlations between them. In this work, we propose an end-to-end task transformer network (T$^2$Net) for joint MRI reconstruction and super-resolution, which allows representations and feature transmission to be shared between multiple task to achieve higher-quality, super-resolved and motion-artifacts-free images from highly undersampled and degenerated MRI data. Our framework combines both reconstruction and super-resolution, divided into two sub-branches, whose features are expressed as queries and keys. Specifically, we encourage joint feature learning between the two tasks, thereby transferring accurate task information. We first use two separate CNN branches to extract task-specific features. Then, a task transformer module is designed to embed and synthesize the relevance between the two tasks. Experimental results show that our multi-task model significantly outperforms advanced sequential methods, both quantitatively and qualitatively.

arXiv:2106.07140공식 코드 · Papers with Code

SinIR: Efficient General Image Manipulation with Single Image Reconstruction

We propose SinIR, an efficient reconstruction-based framework trained on a single natural image for general image manipulation, including super-resolution, editing, harmonization, paint-to-image, photo-realistic style transfer, and artistic style transfer. We train our model on a single image with cascaded multi-scale learning, where each network at each scale is responsible for image reconstruction. This reconstruction objective greatly reduces the complexity and running time of training, compared to the GAN objective. However, the reconstruction objective also exacerbates the output quality. Therefore, to solve this problem, we further utilize simple random pixel shuffling, which also gives control over manipulation, inspired by the Denoising Autoencoder. With quantitative evaluation, we show that SinIR has competitive performance on various image manipulation tasks. Moreover, with a much simpler training objective (i.e., reconstruction), SinIR is trained 33.5 times faster than SinGAN (for 500 X 500 images) that solves similar tasks. Our code is publicly available at github.com/YooJiHyeong/SinIR.

arXiv:2106.06426공식 코드 · Papers with Code

Catch-A-Waveform: Learning to Generate Audio from a Single Short Example

Models for audio generation are typically trained on hours of recordings. Here, we illustrate that capturing the essence of an audio source is typically possible from as little as a few tens of seconds from a single training signal. Specifically, we present a GAN-based generative model that can be trained on one short audio signal from any domain (e.g. speech, music, etc.) and does not require pre-training or any other form of external supervision. Once trained, our model can generate random samples of arbitrary duration that maintain semantic similarity to the training waveform, yet exhibit new compositions of its audio primitives. This enables a long line of interesting applications, including generating new jazz improvisations or new a-cappella rap variants based on a single short example, producing coherent modifications to famous songs (e.g. adding a new verse to a Beatles song based solely on the original recording), filling-in of missing parts (inpainting), extending the bandwidth of a speech signal (super-resolution), and enhancing old recordings without access to any clean training example. We show that in all cases, no more than 20 seconds of training audio commonly suffice for our model to achieve state-of-the-art results. This is despite its complete lack of prior knowledge about the nature of audio signals in general.

arXiv:2106.04428공식 코드 · Papers with Code

Noise Conditional Flow Model for Learning the Super-Resolution Space

Fundamentally, super-resolution is ill-posed problem because a low-resolution image can be obtained from many high-resolution images. Recent studies for super-resolution cannot create diverse super-resolution images. Although SRFlow tried to account for ill-posed nature of the super-resolution by predicting multiple high-resolution images given a low-resolution image, there is room to improve the diversity and visual quality. In this paper, we propose Noise Conditional flow model for Super-Resolution, NCSR, which increases the visual quality and diversity of images through noise conditional layer. To learn more diverse data distribution, we add noise to training data. However, low-quality images are resulted from adding noise. We propose the noise conditional layer to overcome this phenomenon. The noise conditional layer makes our model generate more diverse images with higher visual quality than other works. Furthermore, we show that this layer can overcome data distribution mismatch, a problem that arises in normalizing flow models. With these benefits, NCSR outperforms baseline in diversity and visual quality and achieves better visual quality than traditional GAN-based models. We also get outperformed scores at NTIRE 2021 challenge.

arXiv:2106.04090공식 코드 · Papers with Code

Variational AutoEncoder for Reference based Image Super-Resolution

In this paper, we propose a novel reference based image super-resolution approach via Variational AutoEncoder (RefVAE). Existing state-of-the-art methods mainly focus on single image super-resolution which cannot perform well on large upsampling factors, e.g., 8$\times$. We propose a reference based image super-resolution, for which any arbitrary image can act as a reference for super-resolution. Even using random map or low-resolution image itself, the proposed RefVAE can transfer the knowledge from the reference to the super-resolved images. Depending upon different references, the proposed method can generate different versions of super-resolved images from a hidden super-resolution space. Besides using different datasets for some standard evaluations with PSNR and SSIM, we also took part in the NTIRE2021 SR Space challenge and have provided results of the randomness evaluation of our approach. Compared to other state-of-the-art methods, our approach achieves higher diverse scores.

arXiv:2106.02299공식 코드 · Papers with Code

MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution

Reference-based image super-resolution (RefSR) has shown promising success in recovering high-frequency details by utilizing an external reference image (Ref). In this task, texture details are transferred from the Ref image to the low-resolution (LR) image according to their point- or patch-wise correspondence. Therefore, high-quality correspondence matching is critical. It is also desired to be computationally efficient. Besides, existing RefSR methods tend to ignore the potential large disparity in distributions between the LR and Ref images, which hurts the effectiveness of the information utilization. In this paper, we propose the MASA network for RefSR, where two novel modules are designed to address these problems. The proposed Match & Extraction Module significantly reduces the computational cost by a coarse-to-fine correspondence matching scheme. The Spatial Adaptation Module learns the difference of distribution between the LR and Ref images, and remaps the distribution of Ref features to that of LR features in a spatially adaptive way. This scheme makes the network robust to handle different reference images. Extensive quantitative and qualitative experiments validate the effectiveness of our proposed model.

arXiv:2106.01863공식 코드 · Papers with Code

Robust Reference-based Super-Resolution via C2-Matching

Reference-based Super-Resolution (Ref-SR) has recently emerged as a promising paradigm to enhance a low-resolution (LR) input image by introducing an additional high-resolution (HR) reference image. Existing Ref-SR methods mostly rely on implicit correspondence matching to borrow HR textures from reference images to compensate for the information loss in input images. However, performing local transfer is difficult because of two gaps between input and reference images: the transformation gap (e.g. scale and rotation) and the resolution gap (e.g. HR and LR). To tackle these challenges, we propose C2-Matching in this work, which produces explicit robust matching crossing transformation and resolution. 1) For the transformation gap, we propose a contrastive correspondence network, which learns transformation-robust correspondences using augmented views of the input image. 2) For the resolution gap, we adopt a teacher-student correlation distillation, which distills knowledge from the easier HR-HR matching to guide the more ambiguous LR-HR matching. 3) Finally, we design a dynamic aggregation module to address the potential misalignment issue. In addition, to faithfully evaluate the performance of Ref-SR under a realistic setting, we contribute the Webly-Referenced SR (WR-SR) dataset, mimicking the practical usage scenario. Extensive experiments demonstrate that our proposed C2-Matching significantly outperforms state of the arts by over 1dB on the standard CUFED5 benchmark. Notably, it also shows great generalizability on WR-SR dataset as well as robustness across large scale and rotation transformations.

arXiv:2106.00985공식 코드 · Papers with Code

Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity Estimation

Under stereo settings, the problem of image super-resolution (SR) and disparity estimation are interrelated that the result of each problem could help to solve the other. The effective exploitation of correspondence between different views facilitates the SR performance, while the high-resolution (HR) features with richer details benefit the correspondence estimation. According to this motivation, we propose a Stereo Super-Resolution and Disparity Estimation Feedback Network (SSRDE-FNet), which simultaneously handles the stereo image super-resolution and disparity estimation in a unified framework and interact them with each other to further improve their performance. Specifically, the SSRDE-FNet is composed of two dual recursive sub-networks for left and right views. Besides the cross-view information exploitation in the low-resolution (LR) space, HR representations produced by the SR process are utilized to perform HR disparity estimation with higher accuracy, through which the HR features can be aggregated to generate a finer SR result. Afterward, the proposed HR Disparity Information Feedback (HRDIF) mechanism delivers information carried by HR disparity back to previous layers to further refine the SR image reconstruction. Extensive experiments demonstrate the effectiveness and advancement of SSRDE-FNet.

arXiv:2105.14376공식 코드 · Papers with Code

Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis

The rapid advances in deep generative models over the past years have led to highly {realistic media, known as deepfakes,} that are commonly indistinguishable from real to human eyes. These advances make assessing the authenticity of visual data increasingly difficult and pose a misinformation threat to the trustworthiness of visual content in general. Although recent work has shown strong detection accuracy of such deepfakes, the success largely relies on identifying frequency artifacts in the generated images, which will not yield a sustainable detection approach as generative models continue evolving and closing the gap to real images. In order to overcome this issue, we propose a novel fake detection that is designed to re-synthesize testing images and extract visual cues for detection. The re-synthesis procedure is flexible, allowing us to incorporate a series of visual tasks - we adopt super-resolution, denoising and colorization as the re-synthesis. We demonstrate the improved effectiveness, cross-GAN generalization, and robustness against perturbations of our approach in a variety of detection scenarios involving multiple generators over CelebA-HQ, FFHQ, and LSUN datasets. Source code is available at https://github.com/SSAW14/BeyondtheSpectrum.

arXiv:2105.14951공식 코드 · Papers with Code

SNIPS: Solving Noisy Inverse Problems Stochastically

In this work we introduce a novel stochastic algorithm dubbed SNIPS, which draws samples from the posterior distribution of any linear inverse problem, where the observation is assumed to be contaminated by additive white Gaussian noise. Our solution incorporates ideas from Langevin dynamics and Newton's method, and exploits a pre-trained minimum mean squared error (MMSE) Gaussian denoiser. The proposed approach relies on an intricate derivation of the posterior score function that includes a singular value decomposition (SVD) of the degradation operator, in order to obtain a tractable iterative algorithm for the desired sampling. Due to its stochasticity, the algorithm can produce multiple high perceptual quality samples for the same noisy observation. We demonstrate the abilities of the proposed paradigm for image deblurring, super-resolution, and compressive sensing. We show that the samples produced are sharp, detailed and consistent with the given measurements, and their diversity exposes the inherent uncertainty in the inverse problem being solved.

arXiv:2105.14711공식 코드 · Papers with Code

CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography

Spine-related diseases have high morbidity and cause a huge burden of social cost. Spine imaging is an essential tool for noninvasively visualizing and assessing spinal pathology. Segmenting vertebrae in computed tomography (CT) images is the basis of quantitative medical image analysis for clinical diagnosis and surgery planning of spine diseases. Current publicly available annotated datasets on spinal vertebrae are small in size. Due to the lack of a large-scale annotated spine image dataset, the mainstream deep learning-based segmentation methods, which are data-driven, are heavily restricted. In this paper, we introduce a large-scale spine CT dataset, called CTSpine1K, curated from multiple sources for vertebra segmentation, which contains 1,005 CT volumes with over 11,100 labeled vertebrae belonging to different spinal conditions. Based on this dataset, we conduct several spinal vertebrae segmentation experiments to set the first benchmark. We believe that this large-scale dataset will facilitate further research in many spine-related image analysis tasks, including but not limited to vertebrae segmentation, labeling, 3D spine reconstruction from biplanar radiographs, image super-resolution, and enhancement.

arXiv:2105.13290공식 코드 · Papers with Code

CogView: Mastering Text-to-Image Generation via Transformers

Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding. We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to advance this problem. We also demonstrate the finetuning strategies for various downstream tasks, e.g. style learning, super-resolution, text-image ranking and fashion design, and methods to stabilize pretraining, e.g. eliminating NaN losses. CogView achieves the state-of-the-art FID on the blurred MS COCO dataset, outperforming previous GAN-based models and a recent similar work DALL-E.

arXiv:2105.12409공식 코드 · Papers with Code

Permutation invariance and uncertainty in multitemporal image super-resolution

Recent advances have shown how deep neural networks can be extremely effective at super-resolving remote sensing imagery, starting from a multitemporal collection of low-resolution images. However, existing models have neglected the issue of temporal permutation, whereby the temporal ordering of the input images does not carry any relevant information for the super-resolution task and causes such models to be inefficient with the, often scarce, ground truth data that available for training. Thus, models ought not to learn feature extractors that rely on temporal ordering. In this paper, we show how building a model that is fully invariant to temporal permutation significantly improves performance and data efficiency. Moreover, we study how to quantify the uncertainty of the super-resolved image so that the final user is informed on the local quality of the product. We show how uncertainty correlates with temporal variation in the series, and how quantifying it further improves model performance. Experiments on the Proba-V challenge dataset show significant improvements over the state of the art without the need for self-ensembling, as well as improved data efficiency, reaching the performance of the challenge winner with just 25% of the training data.

arXiv:2105.12038공식 코드 · Papers with Code

Unpaired Depth Super-Resolution in the Wild

Depth maps captured with commodity sensors are often of low quality and resolution; these maps need to be enhanced to be used in many applications. State-of-the-art data-driven methods of depth map super-resolution rely on registered pairs of low- and high-resolution depth maps of the same scenes. Acquisition of real-world paired data requires specialized setups. Another alternative, generating low-resolution maps from high-resolution maps by subsampling, adding noise and other artificial degradation methods, does not fully capture the characteristics of real-world low-resolution images. As a consequence, supervised learning methods trained on such artificial paired data may not perform well on real-world low-resolution inputs. We consider an approach to depth super-resolution based on learning from unpaired data. While many techniques for unpaired image-to-image translation have been proposed, most fail to deliver effective hole-filling or reconstruct accurate surfaces using depth maps. We propose an unpaired learning method for depth super-resolution, which is based on a learnable degradation model, enhancement component and surface normal estimates as features to produce more accurate depth maps. We propose a benchmark for unpaired depth SR and demonstrate that our method outperforms existing unpaired methods and performs on par with paired.

arXiv:2105.11683공식 코드 · Papers with Code

Towards Compact Single Image Super-Resolution via Contrastive Self-distillation

Convolutional neural networks (CNNs) are highly successful for super-resolution (SR) but often require sophisticated architectures with heavy memory cost and computational overhead, significantly restricts their practical deployments on resource-limited devices. In this paper, we proposed a novel contrastive self-distillation (CSD) framework to simultaneously compress and accelerate various off-the-shelf SR models. In particular, a channel-splitting super-resolution network can first be constructed from a target teacher network as a compact student network. Then, we propose a novel contrastive loss to improve the quality of SR images and PSNR/SSIM via explicit knowledge transfer. Extensive experiments demonstrate that the proposed CSD scheme effectively compresses and accelerates several standard SR models such as EDSR, RCAN and CARN. Code is available at https://github.com/Booooooooooo/CSD.

arXiv:2105.10422공식 코드 · Papers with Code

LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond

Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version. Last few years have witnessed impressive progress propelled by deep learning methods. However, one critical challenge faced by existing methods is to strike a sweet spot of deep model complexity and resulting SISR quality. This paper addresses this pain point by proposing a linearly-assembled pixel-adaptive regression network (LAPAR), which casts the direct LR to HR mapping learning into a linear coefficient regression task over a dictionary of multiple predefined filter bases. Such a parametric representation renders our model highly lightweight and easy to optimize while achieving state-of-the-art results on SISR benchmarks. Moreover, based on the same idea, LAPAR is extended to tackle other restoration tasks, e.g., image denoising and JPEG image deblocking, and again, yields strong performance. The code is available at https://github.com/dvlab-research/Simple-SR.