Visuals captured by high-flying aerial drones are increasingly used to assess biodiversity and animal population dynamics around the globe. Yet, challenging acquisition scenarios and tiny animal depictions in airborne imagery, despite ultra-high resolution cameras, have so far been limiting factors for applying computer vision detectors successfully with high confidence. In this paper, we address the problem for the first time by combining deep object detectors with super-resolution techniques and altitude data. In particular, we show that the integration of a holistic attention network based super-resolution approach and a custom-built altitude data exploitation network into standard recognition pipelines can considerably increase the detection efficacy in real-world settings. We evaluate the system on two public, large aerial-capture animal datasets, SAVMAP and AED. We find that the proposed approach can consistently improve over ablated baselines and the state-of-the-art performance for both datasets. In addition, we provide a systematic analysis of the relationship between animal resolution and detection performance. We conclude that super-resolution and altitude knowledge exploitation techniques can significantly increase benchmarks across settings and, thus, should be used routinely when detecting minutely resolved animals in aerial imagery.
In this paper, we propose physics-informed neural operators (PINO) that combine training data and physics constraints to learn the solution operator of a given family of parametric Partial Differential Equations (PDE). PINO is the first hybrid approach incorporating data and PDE constraints at different resolutions to learn the operator. Specifically, in PINO, we combine coarse-resolution training data with PDE constraints imposed at a higher resolution. The resulting PINO model can accurately approximate the ground-truth solution operator for many popular PDE families and shows no degradation in accuracy even under zero-shot super-resolution, i.e., being able to predict beyond the resolution of training data. PINO uses the Fourier neural operator (FNO) framework that is guaranteed to be a universal approximator for any continuous operator and discretization-convergent in the limit of mesh refinement. By adding PDE constraints to FNO at a higher resolution, we obtain a high-fidelity reconstruction of the ground-truth operator. Moreover, PINO succeeds in settings where no training data is available and only PDE constraints are imposed, while previous approaches, such as the Physics-Informed Neural Network (PINN), fail due to optimization challenges, e.g., in multi-scale dynamic systems such as Kolmogorov flows.
Magnetic particle imaging (MPI) offers exceptional contrast for magnetic nanoparticles (MNP) at high spatio-temporal resolution. A common procedure in MPI starts with a calibration scan to measure the system matrix (SM), which is then used to set up an inverse problem to reconstruct images of the MNP distribution during subsequent scans. This calibration enables the reconstruction to sensitively account for various system imperfections. Yet time-consuming SM measurements have to be repeated under notable changes in system properties. Here, we introduce a novel deep learning approach for accelerated MPI calibration based on Transformers for SM super-resolution (TranSMS). Low-resolution SM measurements are performed using large MNP samples for improved signal-to-noise ratio efficiency, and the high-resolution SM is super-resolved via model-based deep learning. TranSMS leverages a vision transformer module to capture contextual relationships in low-resolution input images, a dense convolutional module for localizing high-resolution image features, and a data-consistency module to ensure measurement fidelity. Demonstrations on simulated and experimental data indicate that TranSMS significantly improves SM recovery and MPI reconstruction for up to 64-fold acceleration in two-dimensional imaging.
Field-of-view and resolution trade-offs in X-Ray micro-computed tomography (micro-CT) imaging limit the characterization, analysis and model development of multi-scale porous systems. To this end, we developed an applied methodology utilising deep learning to enhance low resolution images over large sample sizes and create multi-scale models capable of accurately simulating experimental fluid dynamics from the pore (microns) to continuum (centimetres) scale. We develop a 3D Enhanced Deep Super Resolution (EDSR) convolutional neural network to create super resolution (SR) images from low resolution images, which alleviates common micro-CT hardware/reconstruction defects in high-resolution (HR) images. When paired with pore-network simulations and parallel computation, we can create large 3D continuum-scale models with spatially varying flow & material properties. We quantitatively validate the workflow at various scales using direct HR/SR image similarity, pore-scale material/flow simulations and continuum scale multiphase flow experiments (drainage immiscible flow pressures and 3D fluid volume fractions). The SR images and models are comparable to the HR ground truth, and generally accurate to within experimental uncertainty at the continuum scale across a range of flow rates. They are found to be significantly more accurate than their LR counterparts, especially in cases where a wide distribution of pore-sizes are encountered. The applied methodology opens up the possibility to image, model and analyse truly multi-scale heterogeneous systems that are otherwise intractable.
Audio super resolution aims to predict the missing high resolution components of the low resolution audio signals. While audio in nature is a continuous signal, current approaches treat it as discrete data (i.e., input is defined on discrete time domain), and consider the super resolution over a fixed scale factor (i.e., it is required to train a new neural network to change output resolution). To obtain a continuous representation of audio and enable super resolution for arbitrary scale factor, we propose a method of implicit neural representation, coined Local Implicit representation for Super resolution of Arbitrary scale (LISA). Our method locally parameterizes a chunk of audio as a function of continuous time, and represents each chunk with the local latent codes of neighboring chunks so that the function can extrapolate the signal at any time coordinate, i.e., infinite resolution. To learn a continuous representation for audio, we design a self-supervised learning strategy to practice super resolution tasks up to the original resolution by stochastic selection. Our numerical evaluation shows that LISA outperforms the previous fixed-scale methods with a fraction of parameters, but also is capable of arbitrary scale super resolution even beyond the resolution of training data.
Modern neural interfaces allow access to the activity of up to a million neurons within brain circuits. However, bandwidth limits often create a trade-off between greater spatial sampling (more channels or pixels) and the temporal frequency of sampling. Here we demonstrate that it is possible to obtain spatio-temporal super-resolution in neuronal time series by exploiting relationships among neurons, embedded in latent low-dimensional population dynamics. Our novel neural network training strategy, selective backpropagation through time (SBTT), enables learning of deep generative models of latent dynamics from data in which the set of observed variables changes at each time step. The resulting models are able to infer activity for missing samples by combining observations with learned latent dynamics. We test SBTT applied to sequential autoencoders and demonstrate more efficient and higher-fidelity characterization of neural population dynamics in electrophysiological and calcium imaging data. In electrophysiology, SBTT enables accurate inference of neuronal population dynamics with lower interface bandwidths, providing an avenue to significant power savings for implanted neuroelectronic interfaces. In applications to two-photon calcium imaging, SBTT accurately uncovers high-frequency temporal structure underlying neural population activity, substantially outperforming the current state-of-the-art. Finally, we demonstrate that performance could be further improved by using limited, high-bandwidth sampling to pretrain dynamics models, and then using SBTT to adapt these models for sparsely-sampled data.
Pooling layers are essential building blocks of convolutional neural networks (CNNs), to reduce computational overhead and increase the receptive fields of proceeding convolutional operations. Their goal is to produce downsampled volumes that closely resemble the input volume while, ideally, also being computationally and memory efficient. Meeting both these requirements remains a challenge. To this end, we propose an adaptive and exponentially weighted pooling method: adaPool. Our method learns a regional-specific fusion of two sets of pooling kernels that are based on the exponent of the Dice-Sorensen coefficient and the exponential maximum, respectively. AdaPool improves the preservation of detail on a range of tasks including image and video classification and object detection. A key property of adaPool is its bidirectional nature. In contrast to common pooling methods, the learned weights can also be used to upsample activation maps. We term this method adaUnPool. We evaluate adaUnPool on image and video super-resolution and frame interpolation. For benchmarking, we introduce Inter4K, a novel high-quality, high frame-rate video dataset. Our experiments demonstrate that adaPool systematically achieves better results across tasks and backbones, while introducing a minor additional computational and memory overhead.
Single-image super-resolution (SR) with fixed and discrete scale factors has achieved great progress due to the development of deep learning technology. However, the continuous-scale SR, which aims to use a single model to process arbitrary (integer or non-integer) scale factors, is still a challenging task. The existing SR models generally adopt static convolution to extract features, and thus unable to effectively perceive the change of scale factor, resulting in limited generalization performance on multi-scale SR tasks. Moreover, the existing continuous-scale upsampling modules do not make full use of multi-scale features and face problems such as checkerboard artifacts in the SR results and high computational complexity. To address the above problems, we propose a scale-aware dynamic network (SADN) for continuous-scale SR. First, we propose a scale-aware dynamic convolutional (SAD-Conv) layer for the feature learning of multiple SR tasks with various scales. The SAD-Conv layer can adaptively adjust the attention weights of multiple convolution kernels based on the scale factor, which enhances the expressive power of the model with a negligible extra computational cost. Second, we devise a continuous-scale upsampling module (CSUM) with the multi-bilinear local implicit function (MBLIF) for any-scale upsampling. The CSUM constructs multiple feature spaces with gradually increasing scales to approximate the continuous feature representation of an image, and then the MBLIF makes full use of multi-scale features to map arbitrary coordinates to RGB values in high-resolution space. We evaluate our SADN using various benchmarks. The experimental results show that the CSUM can replace the previous fixed-scale upsampling layers and obtain a continuous-scale SR network while maintaining performance. Our SADN uses much fewer parameters and outperforms the state-of-the-art SR methods.
Convolutional Neural Networks (CNNs) have achieved impressive results across many super-resolution (SR) and image restoration tasks. While many such networks can upscale low-resolution (LR) images using just the raw pixel-level information, the ill-posed nature of SR can make it difficult to accurately super-resolve an image which has undergone multiple different degradations. Additional information (metadata) describing the degradation process (such as the blur kernel applied, compression level, etc.) can guide networks to super-resolve LR images with higher fidelity to the original source. Previous attempts at informing SR networks with degradation parameters have indeed been able to improve performance in a number of scenarios. However, due to the fully-convolutional nature of many SR networks, most of these metadata fusion methods either require a complete architectural change, or necessitate the addition of significant extra complexity. Thus, these approaches are difficult to introduce into arbitrary SR networks without considerable design alterations. In this paper, we introduce meta-attention, a simple mechanism which allows any SR CNN to exploit the information available in relevant degradation parameters. The mechanism functions by translating the metadata into a channel attention vector, which in turn selectively modulates the network's feature maps. Incorporating meta-attention into SR networks is straightforward, as it requires no specific type of architecture to function correctly. Extensive testing has shown that meta-attention can consistently improve the pixel-level accuracy of state-of-the-art (SOTA) networks when provided with relevant degradation metadata. For PSNR, the gain on blurred/downsampled (X4) images is of 0.2969 dB (on average) and 0.3320 dB for SOTA general and face SR models, respectively.
High Resolution (HR) medical images provide rich anatomical structure details to facilitate early and accurate diagnosis. In MRI, restricted by hardware capacity, scan time, and patient cooperation ability, isotropic 3D HR image acquisition typically requests long scan time and, results in small spatial coverage and low SNR. Recent studies showed that, with deep convolutional neural networks, isotropic HR MR images could be recovered from low-resolution (LR) input via single image super-resolution (SISR) algorithms. However, most existing SISR methods tend to approach a scale-specific projection between LR and HR images, thus these methods can only deal with a fixed up-sampling rate. For achieving different up-sampling rates, multiple SR networks have to be built up respectively, which is very time-consuming and resource-intensive. In this paper, we propose ArSSR, an Arbitrary Scale Super-Resolution approach for recovering 3D HR MR images. In the ArSSR model, the reconstruction of HR images with different up-scaling rates is defined as learning a continuous implicit voxel function from the observed LR images. Then the SR task is converted to represent the implicit voxel function via deep neural networks from a set of paired HR-LR training examples. The ArSSR model consists of an encoder network and a decoder network. Specifically, the convolutional encoder network is to extract feature maps from the LR input images and the fully-connected decoder network is to approximate the implicit voxel function. Due to the continuity of the learned function, a single ArSSR model can achieve arbitrary up-sampling rate reconstruction of HR images from any input LR image after training. Experimental results on three datasets show that the ArSSR model can achieve state-of-the-art SR performance for 3D HR MR image reconstruction while using a single trained model to achieve arbitrary up-sampling scales.
Images play a vital role in understanding data through visual representation. It gives a clear representation of the object in context. But if this image is not clear it might not be of much use. Thus, the topic of Image Super Resolution arose and many researchers have been working towards applying Computer Vision and Deep Learning Techniques to increase the quality of images. One of the applications of Super Resolution is to increase the quality of Portrait Images. Portrait Images are images which mainly focus on capturing the essence of the main object in the frame, where the object in context is highlighted whereas the background is occluded. When performing Super Resolution the model tries to increase the overall resolution of the image. But in portrait images the foreground resolution is more important than that of the background. In this paper, the performance of a Convolutional Neural Network (CNN) architecture known as U-Net for Super Resolution combined with Mask Region Based CNN (MR-CNN) for foreground super resolution is analysed. This analysis is carried out based on Localized Super Resolution i.e. We pass the LR Images to a pre-trained Image Segmentation model (MR-CNN) and perform super resolution inference on the foreground or Segmented Images and compute the Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR) metrics for comparisons.
Modern digital cameras and smartphones mostly rely on image signal processing (ISP) pipelines to produce realistic colored RGB images. However, compared to DSLR cameras, low-quality images are usually obtained in many portable mobile devices with compact camera sensors due to their physical limitations. The low-quality images have multiple degradations i.e., sub-pixel shift due to camera motion, mosaick patterns due to camera color filter array, low-resolution due to smaller camera sensors, and the rest information are corrupted by the noise. Such degradations limit the performance of current Single Image Super-resolution (SISR) methods in recovering high-resolution (HR) image details from a single low-resolution (LR) image. In this work, we propose a Raw Burst Super-Resolution Iterative Convolutional Neural Network (RBSRICNN) that follows the burst photography pipeline as a whole by a forward (physical) model. The proposed Burst SR scheme solves the problem with classical image regularization, convex optimization, and deep learning techniques, compared to existing black-box data-driven methods. The proposed network produces the final output by an iterative refinement of the intermediate SR estimates. We demonstrate the effectiveness of our proposed approach in quantitative and qualitative experiments that generalize robustly to real LR burst inputs with onl synthetic burst data available for training.
Modelling the impact of a material's mesostructure on device level performance typically requires access to 3D image data containing all the relevant information to define the geometry of the simulation domain. This image data must include sufficient contrast between phases to distinguish each material, be of high enough resolution to capture the key details, but also have a large enough field-of-view to be representative of the material in general. It is rarely possible to obtain data with all of these properties from a single imaging technique. In this paper, we present a method for combining information from pairs of distinct but complementary imaging techniques in order to accurately reconstruct the desired multi-phase, high resolution, representative, 3D images. Specifically, we use deep convolutional generative adversarial networks to implement super-resolution, style transfer and dimensionality expansion. To demonstrate the widespread applicability of this tool, two pairs of datasets are used to validate the quality of the volumes generated by fusing the information from paired imaging techniques. Three key mesostructural metrics are calculated in each case to show the accuracy of this method. Having confidence in the accuracy of our method, we then demonstrate its power by applying to a real data pair from a lithium ion battery electrode, where the required 3D high resolution image data is not available anywhere in the literature. We believe this approach is superior to previously reported statistical material reconstruction methods both in terms of its fidelity and ease of use. Furthermore, much of the data required to train this algorithm already exists in the literature, waiting to be combined. As such, our open-access code could precipitate a step change by generating the hard to obtain high quality image volumes necessary to simulate behaviour at the mesoscale.
Despite the growing popularity of video super-resolution (VSR), there is still no good way to assess the quality of the restored details in upscaled frames. Some SR methods may produce the wrong digit or an entirely different face. Whether a method's results are trustworthy depends on how well it restores truthful details. Image super-resolution can use natural distributions to produce a high-resolution image that is only somewhat similar to the real one. VSR enables exploration of additional information in neighboring frames to restore details from the original scene. The ERQA metric, which we propose in this paper, aims to estimate a model's ability to restore real details using VSR. On the assumption that edges are significant for detail and character recognition, we chose edge fidelity as the foundation for this metric. Experimental validation of our work is based on the MSU Video Super-Resolution Benchmark, which includes the most difficult patterns for detail restoration and verifies the fidelity of details from the original frame. Code for the proposed metric is publicly available at https://github.com/msu-video-group/ERQA.
In this paper, we consider the problem of reference-based video super-resolution(RefVSR), i.e., how to utilize a high-resolution (HR) reference frame to super-resolve a low-resolution (LR) video sequence. The existing approaches to RefVSR essentially attempt to align the reference and the input sequence, in the presence of resolution gap and long temporal range. However, they either ignore temporal structure within the input sequence, or suffer accumulative alignment errors. To address these issues, we propose EFENet to exploit simultaneously the visual cues contained in the HR reference and the temporal information contained in the LR sequence. EFENet first globally estimates cross-scale flow between the reference and each LR frame. Then our novel flow refinement module of EFENet refines the flow regarding the furthest frame using all the estimated flows, which leverages the global temporal information within the sequence and therefore effectively reduces the alignment errors. We provide comprehensive evaluations to validate the strengths of our approach, and to demonstrate that the proposed framework outperforms the state-of-the-art methods. Code is available at https://github.com/IndigoPurple/EFENet.
Adversarial attacks can generate adversarial inputs by applying small but intentionally worst-case perturbations to samples from the dataset, which leads to even state-of-the-art deep neural networks outputting incorrect answers with high confidence. Hence, some adversarial defense techniques are developed to improve the security and robustness of the models and avoid them being attacked. Gradually, a game-like competition between attackers and defenders formed, in which both players would attempt to play their best strategies against each other while maximizing their own payoffs. To solve the game, each player would choose an optimal strategy against the opponent based on the prediction of the opponent's strategy choice. In this work, we are on the defensive side to apply game-theoretic approaches on defending against attacks. We use two randomization methods, random initialization and stochastic activation pruning, to create diversity of networks. Furthermore, we use one denoising technique, super resolution, to improve models' robustness by preprocessing images before attacks. Our experimental results indicate that those three methods can effectively improve the robustness of deep-learning neural networks.
Multi-focus image fusion (MFIF) and super-resolution (SR) are the inverse problem of imaging model, purposes of MFIF and SR are obtaining all-in-focus and high-resolution 2D mapping of targets. Though various MFIF and SR methods have been designed; almost all the them deal with MFIF and SR separately. This paper unifies MFIF and SR problems in the physical perspective as the multi-focus image super resolution fusion (MFISRF), and we propose a novel unified dataset-free unsupervised framework named deep fusion prior (DFP) based-on deep image prior (DIP) to address such MFISRF with single model. Experiments have proved that our proposed DFP approaches or even outperforms those state-of-art MFIF and SR method combinations. To our best knowledge, our proposed work is a dataset-free unsupervised method to simultaneously implement the multi-focus fusion and super-resolution task for the first time. Additionally, DFP is a general framework, thus its networks and focus measurement tactics can be continuously updated to further improve the MFISRF performance. DFP codes are open source available at http://github.com/GuYuanjie/DeepFusionPrior.
Synthesizing multimodality medical data provides complementary knowledge and helps doctors make precise clinical decisions. Although promising, existing multimodal brain graph synthesis frameworks have several limitations. First, they mainly tackle only one problem (intra- or inter-modality), limiting their generalizability to synthesizing inter- and intra-modality simultaneously. Second, while few techniques work on super-resolving low-resolution brain graphs within a single modality (i.e., intra), inter-modality graph super-resolution remains unexplored though this would avoid the need for costly data collection and processing. More importantly, both target and source domains might have different distributions, which causes a domain fracture between them. To fill these gaps, we propose a multi-resolution StairwayGraphNet (SG-Net) framework to jointly infer a target graph modality based on a given modality and super-resolve brain graphs in both inter and intra domains. Our SG-Net is grounded in three main contributions: (i) predicting a target graph from a source one based on a novel graph generative adversarial network in both inter (e.g., morphological-functional) and intra (e.g., functional-functional) domains, (ii) generating high-resolution brain graphs without resorting to the time consuming and expensive MRI processing steps, and (iii) enforcing the source distribution to match that of the ground truth graphs using an inter-modality aligner to relax the loss function to optimize. Moreover, we design a new Ground Truth-Preserving loss function to guide both generators in learning the topological structure of ground truth brain graphs more accurately. Our comprehensive experiments on predicting target brain graphs from source graphs using a multi-resolution stairway showed the outperformance of our method in comparison with its variants and state-of-the-art method.
Accurate and automated super-resolution image synthesis is highly desired since it has the great potential to circumvent the need for acquiring high-cost medical scans and a time-consuming preprocessing pipeline of neuroimaging data. However, existing deep learning frameworks are solely designed to predict high-resolution (HR) image from a low-resolution (LR) one, which limits their generalization ability to brain graphs (i.e., connectomes). A small body of works has focused on superresolving brain graphs where the goal is to predict a HR graph from a single LR graph. Although promising, existing works mainly focus on superresolving graphs belonging to the same domain (e.g., functional), overlooking the domain fracture existing between multimodal brain data distributions (e.g., morphological and structural). To this aim, we propose a novel inter-domain adaptation framework namely, Learn to SuperResolve Brain Graphs with Knowledge Distillation Network (L2S-KDnet), which adopts a teacher-student paradigm to superresolve brain graphs. Our teacher network is a graph encoder-decoder that firstly learns the LR brain graph embeddings, and secondly learns how to align the resulting latent representations to the HR ground truth data distribution using an adversarial regularization. Ultimately, it decodes the HR graphs from the aligned embeddings. Next, our student network learns the knowledge of the aligned brain graphs as well as the topological structure of the predicted HR graphs transferred from the teacher. We further leverage the decoder of the teacher to optimize the student network. L2S-KDnet presents the first TS architecture tailored for brain graph super-resolution synthesis that is based on inter-domain alignment. Our experimental results demonstrate substantial performance gains over benchmark methods.
Modern handheld devices can acquire burst image sequence in a quick succession. However, the individual acquired frames suffer from multiple degradations and are misaligned due to camera shake and object motions. The goal of Burst Image Restoration is to effectively combine complimentary cues across multiple burst frames to generate high-quality outputs. Towards this goal, we develop a novel approach by solely focusing on the effective information exchange between burst frames, such that the degradations get filtered out while the actual scene details are preserved and enhanced. Our central idea is to create a set of pseudo-burst features that combine complementary information from all the input burst frames to seamlessly exchange information. However, the pseudo-burst cannot be successfully created unless the individual burst frames are properly aligned to discount inter-frame movements. Therefore, our approach initially extracts pre-processed features from each burst frame and matches them using an edge-boosting burst alignment module. The pseudo-burst features are then created and enriched using multi-scale contextual information. Our final step is to adaptively aggregate information from the pseudo-burst features to progressively increase resolution in multiple stages while merging the pseudo-burst features. In comparison to existing works that usually follow a late fusion scheme with single-stage upsampling, our approach performs favorably, delivering state-of-the-art performance on burst superresolution, burst low-light image enhancement, and burst denoising tasks. The source code and pre-trained models are available at \url{https://github.com/akshaydudhane16/BIPNet}.