Direct time-of-flight (dToF) sensors are promising for next-generation on-device 3D sensing. However, limited by manufacturing capabilities in a compact module, the dToF data has a low spatial resolution (e.g., $\sim 20\times30$ for iPhone dToF), and it requires a super-resolution step before being passed to downstream tasks. In this paper, we solve this super-resolution problem by fusing the low-resolution dToF data with the corresponding high-resolution RGB guidance. Unlike the conventional RGB-guided depth enhancement approaches, which perform the fusion in a per-frame manner, we propose the first multi-frame fusion scheme to mitigate the spatial ambiguity resulting from the low-resolution dToF imaging. In addition, dToF sensors provide unique depth histogram information for each local patch, and we incorporate this dToF-specific feature in our network design to further alleviate spatial ambiguity. To evaluate our models on complex dynamic indoor environments and to provide a large-scale dToF sensor dataset, we introduce DyDToF, the first synthetic RGB-dToF video dataset that features dynamic objects and a realistic dToF simulator following the physical imaging process. We believe the methods and dataset are beneficial to a broad community as dToF depth sensing is becoming mainstream on mobile devices. Our code and data are publicly available: https://github.com/facebookresearch/DVSR/
Separation of multiple singing voices into each voice is a rarely studied area in music source separation research. The absence of a benchmark dataset has hindered its progress. In this paper, we present an evaluation dataset and provide baseline studies for multiple singing voices separation. First, we introduce MedleyVox, an evaluation dataset for multiple singing voices separation. We specify the problem definition in this dataset by categorizing it into i) unison, ii) duet, iii) main vs. rest, and iv) N-singing separation. Second, to overcome the absence of existing multi-singing datasets for a training purpose, we present a strategy for construction of multiple singing mixtures using various single-singing datasets. Third, we propose the improved super-resolution network (iSRNet), which greatly enhances initial estimates of separation networks. Jointly trained with the Conv-TasNet and the multi-singing mixture construction strategy, the proposed iSRNet achieved comparable performance to ideal time-frequency masks on duet and unison subsets of MedleyVox. Audio samples, the dataset, and codes are available on our website (https://github.com/jeonchangbin49/MedleyVox).
Due to the development of deep learning-based denoisers, the plug-and-play strategy has achieved great success in image restoration problems. However, existing plug-and-play image restoration methods are designed for non-blind Gaussian denoising such as zhang et al (2022), the performance of which visibly deteriorate for unknown noises. To push the limits of plug-and-play image restoration, we propose a novel framework with blind Gaussian prior, which can deal with more complicated image restoration problems in the real world. More specifically, we build up a new image restoration model by regarding the noise level as a variable, which is implemented by a two-stage blind Gaussian denoiser consisting of a noise estimation subnetwork and a denoising subnetwork, where the noise estimation subnetwork provides the noise level to the denoising subnetwork for blind noise removal. We also introduce the curvature map into the encoder-decoder architecture and the supervised attention module to achieve a highly flexible and effective convolutional neural network. The experimental results on image denoising, deblurring and single-image super-resolution are provided to demonstrate the advantages of our deep curvature denoiser and the resulting plug-and-play blind image restoration method over the state-of-the-art model-based and learning-based methods. Our model is shown to be able to recover the fine image details and tiny structures even when the noise level is unknown for different image restoration tasks. The source codes are available at https://github.com/Duanlab123/CurvPnP.
To date, the best-performing blind super-resolution (SR) techniques follow one of two paradigms: A) generate and train a standard SR network on synthetic low-resolution - high-resolution (LR - HR) pairs or B) attempt to predict the degradations an LR image has suffered and use these to inform a customised SR network. Despite significant progress, subscribers to the former miss out on useful degradation information that could be used to improve the SR process. On the other hand, followers of the latter rely on weaker SR networks, which are significantly outperformed by the latest architectural advancements. In this work, we present a framework for combining any blind SR prediction mechanism with any deep SR network, using a metadata insertion block to insert prediction vectors into SR network feature maps. Through comprehensive testing, we prove that state-of-the-art contrastive and iterative prediction schemes can be successfully combined with high-performance SR networks such as RCAN and HAN within our framework. We show that our hybrid models consistently achieve stronger SR performance than both their non-blind and blind counterparts. Furthermore, we demonstrate our framework's robustness by predicting degradations and super-resolving images from a complex pipeline of blurring, noise and compression.
Face Restoration (FR) aims to restore High-Quality (HQ) faces from Low-Quality (LQ) input images, which is a domain-specific image restoration problem in the low-level computer vision area. The early face restoration methods mainly use statistic priors and degradation models, which are difficult to meet the requirements of real-world applications in practice. In recent years, face restoration has witnessed great progress after stepping into the deep learning era. However, there are few works to study deep learning-based face restoration methods systematically. Thus, this paper comprehensively surveys recent advances in deep learning techniques for face restoration. Specifically, we first summarize different problem formulations and analyze the characteristic of the face image. Second, we discuss the challenges of face restoration. Concerning these challenges, we present a comprehensive review of existing FR methods, including prior based methods and deep learning-based methods. Then, we explore developed techniques in the task of FR covering network architectures, loss functions, and benchmark datasets. We also conduct a systematic benchmark evaluation on representative methods. Finally, we discuss future directions, including network designs, metrics, benchmark datasets, applications,etc. We also provide an open-source repository for all the discussed methods, which is available at https://github.com/TaoWangzj/Awesome-Face-Restoration.
Video super-resolution (VSR) is a task that aims to reconstruct high-resolution (HR) frames from the low-resolution (LR) reference frame and multiple neighboring frames. The vital operation is to utilize the relative misaligned frames for the current frame reconstruction and preserve the consistency of the results. Existing methods generally explore information propagation and frame alignment to improve the performance of VSR. However, few studies focus on the temporal consistency of inter-frames. In this paper, we propose a Temporal Consistency learning Network (TCNet) for VSR in an end-to-end manner, to enhance the consistency of the reconstructed videos. A spatio-temporal stability module is designed to learn the self-alignment from inter-frames. Especially, the correlative matching is employed to exploit the spatial dependency from each frame to maintain structural stability. Moreover, a self-attention mechanism is utilized to learn the temporal correspondence to implement an adaptive warping operation for temporal consistency among multi-frames. Besides, a hybrid recurrent architecture is designed to leverage short-term and long-term information. We further present a progressive fusion module to perform a multistage fusion of spatio-temporal features. And the final reconstructed frames are refined by these fused features. Objective and subjective results of various experiments demonstrate that TCNet has superior performance on different benchmark datasets, compared to several state-of-the-art methods.
We study the interpolation capabilities of implicit neural representations (INRs) of images. In principle, INRs promise a number of advantages, such as continuous derivatives and arbitrary sampling, being freed from the restrictions of a raster grid. However, empirically, INRs have been observed to poorly interpolate between the pixels of the fit image; in other words, they do not inherently possess a suitable prior for natural images. In this paper, we propose to address and improve INRs' interpolation capabilities by explicitly integrating image prior information into the INR architecture via deep decoder, a specific implementation of the deep image prior (DIP). Our method, which we call TITAN, leverages a residual connection from the input which enables integrating the principles of the grid-based DIP into the grid-free INR. Through super-resolution and computed tomography experiments, we demonstrate that our method significantly improves upon classic INRs, thanks to the induced natural image bias. We also find that by constraining the weights to be sparse, image quality and sharpness are enhanced, increasing the Lipschitz constant.
Diffusion probabilistic model (DPM) recently becomes one of the hottest topic in computer vision. Its image generation application such as Imagen, Latent Diffusion Models and Stable Diffusion have shown impressive generation capabilities, which aroused extensive discussion in the community. Many recent studies also found it is useful in many other vision tasks, like image deblurring, super-resolution and anomaly detection. Inspired by the success of DPM, we propose the first DPM based model toward general medical image segmentation tasks, which we named MedSegDiff. In order to enhance the step-wise regional attention in DPM for the medical image segmentation, we propose dynamic conditional encoding, which establishes the state-adaptive conditions for each sampling step. We further propose Feature Frequency Parser (FF-Parser), to eliminate the negative effect of high-frequency noise component in this process. We verify MedSegDiff on three medical segmentation tasks with different image modalities, which are optic cup segmentation over fundus images, brain tumor segmentation over MRI images and thyroid nodule segmentation over ultrasound images. The experimental results show that MedSegDiff outperforms state-of-the-art (SOTA) methods with considerable performance gap, indicating the generalization and effectiveness of the proposed model. Our code is released at https://github.com/WuJunde/MedSegDiff.
When handling complicated text images (e.g., irregular structures, low resolution, heavy occlusion, and uneven illumination), existing supervised text recognition methods are data-hungry. Although these methods employ large-scale synthetic text images to reduce the dependence on annotated real images, the domain gap still limits the recognition performance. Therefore, exploring the robust text feature representations on unlabeled real images by self-supervised learning is a good solution. However, existing self-supervised text recognition methods conduct sequence-to-sequence representation learning by roughly splitting the visual features along the horizontal axis, which limits the flexibility of the augmentations, as large geometric-based augmentations may lead to sequence-to-sequence feature inconsistency. Motivated by this, we propose a novel self-supervised Character-to-Character Distillation method, CCD, which enables versatile augmentations to facilitate general text representation learning. Specifically, we delineate the character structures of unlabeled real images by designing a self-supervised character segmentation module. Following this, CCD easily enriches the diversity of local characters while keeping their pairwise alignment under flexible augmentations, using the transformation matrix between two augmented views from images. Experiments demonstrate that CCD achieves state-of-the-art results, with average performance gains of 1.38% in text recognition, 1.7% in text segmentation, 0.24 dB (PSNR) and 0.0321 (SSIM) in text super-resolution. Code is available at https://github.com/TongkunGuan/CCD.
In computational imaging, hardware for signal sampling and software for object reconstruction are designed in tandem for improved capability. Examples of such systems include computed tomography (CT), magnetic resonance imaging (MRI), and superresolution microscopy. In contrast to more traditional cameras, in these devices, indirect measurements are taken and computational algorithms are used for reconstruction. This allows for advanced capabilities such as super-resolution or 3-dimensional imaging, pushing forward the frontier of scientific discovery. However, these techniques generally require a large number of measurements, causing low throughput, motion artifacts, and/or radiation damage, limiting applications. Data-driven approaches to reducing the number of measurements needed have been proposed, but they predominately require a ground truth or reference dataset, which may be impossible to collect. This work outlines a self-supervised approach and explores the future work that is necessary to make such a technique usable for real applications. Light-emitting diode (LED) array microscopy, a modality that allows visualization of transparent objects in two and three dimensions with high resolution and field-of-view, is used as an illustrative example. We release our code at https://github.com/vganapati/LED_PVAE and our experimental data at https://doi.org/10.6084/m9.figshare.21232088 .
In the absence of high-resolution samples, super-resolution of sparse observations on dynamical systems is a challenging problem with wide-reaching applications in experimental settings. We showcase the application of physics-informed convolutional neural networks for super-resolution of sparse observations on grids. Results are shown for the chaotic-turbulent Kolmogorov flow, demonstrating the potential of this method for resolving finer scales of turbulence when compared with classic interpolation methods, and thus effectively reconstructing missing physics.
The License Plate Recognition (LPR) field has made impressive advances in the last decade due to novel deep learning approaches combined with the increased availability of training data. However, it still has some open issues, especially when the data come from low-resolution (LR) and low-quality images/videos, as in surveillance systems. This work focuses on license plate (LP) reconstruction in LR and low-quality images. We present a Single-Image Super-Resolution (SISR) approach that extends the attention/transformer module concept by exploiting the capabilities of PixelShuffle layers and that has an improved loss function based on LPR predictions. For training the proposed architecture, we use synthetic images generated by applying heavy Gaussian noise in terms of Structural Similarity Index Measure (SSIM) to the original high-resolution (HR) images. In our experiments, the proposed method outperformed the baselines both quantitatively and qualitatively. The datasets we created for this work are publicly available to the research community at https://github.com/valfride/lpr-rsr/
Neural audio super-resolution models are typically trained on low- and high-resolution audio signal pairs. Although these methods achieve highly accurate super-resolution if the acoustic characteristics of the input data are similar to those of the training data, challenges remain: the models suffer from quality degradation for out-of-domain data, and paired data are required for training. To address these problems, we propose Dual-CycleGAN, a high-quality audio super-resolution method that can utilize unpaired data based on two connected cycle consistent generative adversarial networks (CycleGAN). Our method decomposes the super-resolution method into domain adaptation and resampling processes to handle acoustic mismatch in the unpaired low- and high-resolution signals. The two processes are then jointly optimized within the CycleGAN framework. Experimental results verify that the proposed method significantly outperforms conventional methods when paired data are not available. Code and audio samples are available from https://chomeyama.github.io/DualCycleGAN-Demo/.
Recently, diffusion models (DMs) have been increasingly used in audio processing tasks, including speech super-resolution (SR), which aims to restore high-frequency content given low-resolution speech utterances. This is commonly achieved by conditioning the network of noise predictor with low-resolution audio. In this paper, we propose a novel sampling algorithm that communicates the information of the low-resolution audio via the reverse sampling process of DMs. The proposed method can be a drop-in replacement for the vanilla sampling process and can significantly improve the performance of the existing works. Moreover, by coupling the proposed sampling method with an unconditional DM, i.e., a DM with no auxiliary inputs to its noise predictor, we can generalize it to a wide range of SR setups. We also attain state-of-the-art results on the VCTK Multi-Speaker benchmark with this novel formulation.
High resolution (HR) 3D images are widely used nowadays, such as medical images like Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). However, segmentation of these 3D images remains a challenge due to their high spatial resolution and dimensionality in contrast to currently limited GPU memory. Therefore, most existing 3D image segmentation methods use patch-based models, which have low inference efficiency and ignore global contextual information. To address these problems, we propose a super-resolution (SR) based patch-free 3D image segmentation framework that can realize HR segmentation from a global-wise low-resolution (LR) input. The framework contains two sub-tasks, of which semantic segmentation is the main task and super resolution is an auxiliary task aiding in rebuilding the high frequency information from the LR input. To furthermore balance the information loss with the LR input, we propose a High-Frequency Guidance Module (HGM), and design an efficient selective cropping algorithm to crop an HR patch from the original image as restoration guidance for it. In addition, we also propose a Task-Fusion Module (TFM) to exploit the inter connections between segmentation and SR task, realizing joint optimization of the two tasks. When predicting, only the main segmentation task is needed, while other modules can be removed for acceleration. The experimental results on two different datasets show that our framework has a four times higher inference speed compared to traditional patch-based methods, while its performance also surpasses other patch-based and patch-free models.
Diffusion models have shown great results in image generation and in image editing. However, current approaches are limited to low resolutions due to the computational cost of training diffusion models for high-resolution generation. We propose an approach that uses a pre-trained low-resolution diffusion model to edit images in the megapixel range. We first use Blended Diffusion to edit the image at a low resolution, and then upscale it in multiple stages, using a super-resolution model and Blended Diffusion. Using our approach, we achieve higher visual fidelity than by only applying off the shelf super-resolution methods to the output of the diffusion model. We also obtain better global consistency than directly using the diffusion model at a higher resolution.
In this paper, we introduce a novel implicit neural network for the task of single image super-resolution at arbitrary scale factors. To do this, we represent an image as a decoding function that maps locations in the image along with their associated features to their reciprocal pixel attributes. Since the pixel locations are continuous in this representation, our method can refer to any location in an image of varying resolution. To retrieve an image of a particular resolution, we apply a decoding function to a grid of locations each of which refers to the center of a pixel in the output image. In contrast to other techniques, our dual interactive neural network decouples content and positional features. As a result, we obtain a fully implicit representation of the image that solves the super-resolution problem at (real-valued) elective scales using a single model. We demonstrate the efficacy and flexibility of our approach against the state of the art on publicly available benchmark datasets.
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level vision tasks operate in the RAW domain (e.g. image denoising, white balance) due to its linear relationship with the scene irradiance, wide-range of information at 12bits, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public RGB datasets. This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, "reverse" the ISP transformation. The proposed methods and benchmark establish the state-of-the-art for this low-level vision inverse problem, and generating realistic raw sensor readings can potentially benefit other tasks such as denoising and super-resolution.
Plug & Play methods combine proximal algorithms with denoiser priors to solve inverse problems. These methods rely on the computability of the proximal operator of the data fidelity term. In this paper, we propose a Plug & Play framework based on linearized ADMM that allows us to bypass the computation of intractable proximal operators. We demonstrate the convergence of the algorithm and provide results on restoration tasks such as super-resolution and deblurring with non-uniform blur.
Deep learning-based algorithms have greatly improved the performance of remote sensing image (RSI) super-resolution (SR). However, increasing network depth and parameters cause a huge burden of computing and storage. Directly reducing the depth or width of existing models results in a large performance drop. We observe that the SR difficulty of different regions in an RSI varies greatly, and existing methods use the same deep network to process all regions in an image, resulting in a waste of computing resources. In addition, existing SR methods generally predefine integer scale factors and cannot perform stepless SR, i.e., a single model can deal with any potential scale factor. Retraining the model on each scale factor wastes considerable computing resources and model storage space. To address the above problems, we propose a saliency-aware dynamic routing network (SalDRN) for lightweight and stepless SR of RSIs. First, we introduce visual saliency as an indicator of region-level SR difficulty and integrate a lightweight saliency detector into the SalDRN to capture pixel-level visual characteristics. Then, we devise a saliency-aware dynamic routing strategy that employs path selection switches to adaptively select feature extraction paths of appropriate depth according to the SR difficulty of sub-image patches. Finally, we propose a novel lightweight stepless upsampling module whose core is an implicit feature function for realizing mapping from low-resolution feature space to high-resolution feature space. Comprehensive experiments verify that the SalDRN can achieve a good trade-off between performance and complexity. The code is available at \url{https://github.com/hanlinwu/SalDRN}.