Diego Valsesia

Emanuele Aiello, Diego Valsesia, Enrico Magli

Denoising Diffusion Models (DDMs) have become a popular tool for generating high-quality samples from complex data distributions. These models are able to capture sophisticated patterns and structures in the data, and can generate samples that are highly diverse and representative of the underlying distribution. However, one of the main limitations of diffusion models is the complexity of sample generation, since a large number of inference timesteps is required to faithfully capture the data distribution. In this paper, we present MMD-DDM, a novel method for fast sampling of diffusion models. Our approach is based on the idea of using the Maximum Mean Discrepancy (MMD) to finetune the learned distribution with a given budget of timesteps. This allows the finetuned model to significantly improve the speed-quality trade-off, by substantially increasing fidelity in inference regimes with few steps or, equivalently, by reducing the required number of steps to reach a target fidelity, thus paving the way for a more practical adoption of diffusion models in a wide range of applications. We evaluate our approach on unconditional image generation with extensive experiments across the CIFAR-10, CelebA, ImageNet and LSUN-Church datasets. Our findings show that the proposed method is able to produce high-quality samples in a fraction of the time required by widely-used diffusion models, and outperforms state-of-the-art techniques for accelerated sampling. Code is available at: https://github.com/diegovalsesia/MMD-DDM.

Emanuele Aiello, Diego Valsesia, Enrico Magli

In this paper we explore the recent topic of point cloud completion, guided by an auxiliary image. We show how it is possible to effectively combine the information from the two modalities in a localized latent space, thus avoiding the need for complex point cloud reconstruction methods from single views used by the state-of-the-art. We also investigate a novel weakly-supervised setting where the auxiliary image provides a supervisory signal to the training process by using a differentiable renderer on the completed point cloud to measure fidelity in the image space. Experiments show significant improvements over state-of-the-art supervised methods for both unimodal and multimodal completion. We also show the effectiveness of the weakly-supervised approach which outperforms a number of supervised methods and is competitive with the latest supervised models only exploiting point cloud information.

Antonio Montanaro, Diego Valsesia, Enrico Magli

Point clouds of 3D objects exhibit an inherent compositional nature where simple parts can be assembled into progressively more complex shapes to form whole objects. Explicitly capturing such part-whole hierarchy is a long-sought objective in order to build effective models, but its tree-like nature has made the task elusive. In this paper, we propose to embed the features of a point cloud classifier into the hyperbolic space and explicitly regularize the space to account for the part-whole hierarchy. The hyperbolic space is the only space that can successfully embed the tree-like nature of the hierarchy. This leads to substantial improvements in the performance of state-of-art supervised models for point cloud classification.

Antonio Montanaro, Diego Valsesia, Enrico Magli

Inverse problems consist in reconstructing signals from incomplete sets of measurements and their performance is highly dependent on the quality of the prior knowledge encoded via regularization. While traditional approaches focus on obtaining a unique solution, an emerging trend considers exploring multiple feasibile solutions. In this paper, we propose a method to generate multiple reconstructions that fit both the measurements and a data-driven prior learned by a generative adversarial network. In particular, we show that, starting from an initial solution, it is possible to find directions in the latent space of the generative model that are null to the forward operator, and thus keep consistency with the measurements, while inducing significant perceptual change. Our exploration approach allows to generate multiple solutions to the inverse problem an order of magnitude faster than existing approaches; we show results on image super-resolution and inpainting problems.

Diego Valsesia, Enrico Magli

Multi-image super-resolution from multi-temporal satellite acquisitions of a scene has recently enjoyed great success thanks to new deep learning models. In this paper, we go beyond classic image reconstruction at a higher resolution by studying a super-resolved inference problem, namely semantic segmentation at a spatial resolution higher than the one of sensing platform. We expand upon recently proposed models exploiting temporal permutation invariance with a multi-resolution fusion module able to infer the rich semantic information needed by the segmentation task. The model presented in this paper has recently won the AI4EO challenge on Enhanced Sentinel 2 Agriculture.

Ziyao Yi, Davide Piccinini, Diego Valsesia et al.

The next generation of Earth observation satellites will seek to deploy intelligent models directly onboard the payload in order to minimize the latency incurred by the transmission and processing chain of the ground segment, for time-critical applications. Designing neural architectures for onboard execution, particularly for satellite-based hyperspectral imagers, poses novel challenges due to the unique constraints of this environment and imaging system that are largely unexplored by the traditional computer vision literature. In this paper, we show that this setting requires addressing three competing objectives, namely high-quality inference with low complexity, dynamic power scalability and fault tolerance. We focus on the problem of hyperspectral image denoising, which is a critical task to enable effective downstream inference, and highlights the constraints of the onboard processing scenario. We propose a neural network design that addresses the three aforementioned objectives with several novel contributions. In particular, we propose a mixture of denoisers that can be resilient to radiation-induced faults as well as allowing for time-varying power scaling. Moreover, each denoiser employs an innovative architecture where an image is processed line-by-line in a causal way, with a memory of past lines, in order to match the acquisition process of pushbroom hyperspectral sensors and greatly limit memory requirements. We show that the proposed architecture can run in real-time, i.e., process one line in the time it takes to acquire the next one, on low-power hardware and provide competitive denoising quality with respect to significantly more complex state-of-the-art models. We also show that the power scalability and fault tolerance objectives provide a design space with multiple tradeoffs between those properties and denoising quality.

Ziyao Yi, Diego Valsesia, Tiziano Bianchi et al.

Image deblurring is a challenging problem in imaging due to its highly ill-posed nature. Deep learning models have shown great success in tackling this problem but the quest for the best image quality has brought their computational complexity up, making them impractical on anything but powerful servers. Meanwhile, recent works have shown that mobile Lidars can provide complementary information in the form of depth maps that enhance deblurring quality. In this paper, we introduce a novel low-complexity neural network for depth-guided image deblurring. We show that the use of the wavelet transform to separate structural details and reduce spatial redundancy as well as efficient feature conditioning on the depth information are essential ingredients in developing a low-complexity model. Experimental results show competitive image quality against recent state-of-the-art models while reducing complexity by up to two orders of magnitude.

Luca Savant Aira, Antonio Montanaro, Emanuele Aiello et al.

Generating videos with realistic and physically plausible motion is one of the main recent challenges in computer vision. While diffusion models are achieving compelling results in image generation, video diffusion models are limited by heavy training and huge models, resulting in videos that are still biased to the training dataset. In this work we propose MotionCraft, a new zero-shot video generator to craft physics-based and realistic videos. MotionCraft is able to warp the noise latent space of an image diffusion model, such as Stable Diffusion, by applying an optical flow derived from a physics simulation. We show that warping the noise latent space results in coherent application of the desired motion while allowing the model to generate missing elements consistent with the scene evolution, which would otherwise result in artefacts or missing content if the flow was applied in the pixel space. We compare our method with the state-of-the-art Text2Video-Zero reporting qualitative and quantitative improvements, demonstrating the effectiveness of our approach to generate videos with finely-prescribed complex motion dynamics. Project page: https://mezzelfo.github.io/MotionCraft/

Luca Savant, Diego Valsesia, Enrico Magli

We present Stochastic Gaussian Splatting (SGS): the first framework for uncertainty estimation using Gaussian Splatting (GS). GS recently advanced the novel-view synthesis field by achieving impressive reconstruction quality at a fraction of the computational cost of Neural Radiance Fields (NeRF). However, contrary to the latter, it still lacks the ability to provide information about the confidence associated with their outputs. To address this limitation, in this paper, we introduce a Variational Inference-based approach that seamlessly integrates uncertainty prediction into the common rendering pipeline of GS. Additionally, we introduce the Area Under Sparsification Error (AUSE) as a new term in the loss function, enabling optimization of uncertainty estimation alongside image reconstruction. Experimental results on the LLFF dataset demonstrate that our method outperforms existing approaches in terms of both image rendering quality and uncertainty estimation accuracy. Overall, our framework equips practitioners with valuable insights into the reliability of synthesized views, facilitating safer decision-making in real-world applications.

Diego Valsesia, Tiziano Bianchi, Enrico Magli

Deep learning methods have traditionally been difficult to apply to compression of hyperspectral images onboard of spacecrafts, due to the large computational complexity needed to achieve adequate representational power, as well as the lack of suitable datasets for training and testing. In this paper, we depart from the traditional autoencoder approach and we design a predictive neural network, called LineRWKV, that works recursively line-by-line to limit memory consumption. In order to achieve that, we adopt a novel hybrid attentive-recursive operation that combines the representational advantages of Transformers with the linear complexity and recursive implementation of recurrent neural networks. The compression algorithm performs prediction of each pixel using LineRWKV, followed by entropy coding of the residual. Experiments on the HySpecNet-11k dataset and PRISMA images show that LineRWKV is the first deep-learning method to outperform CCSDS-123.0-B-2 at lossless and near-lossless compression. Promising throughput results are also evaluated on a 7W embedded system.

Emanuele Aiello, Umberto Michieli, Diego Valsesia et al.

Personalized image generation requires text-to-image generative models that capture the core features of a reference subject to allow for controlled generation across different contexts. Existing methods face challenges due to complex training requirements, high inference costs, limited flexibility, or a combination of these issues. In this paper, we introduce DreamCache, a scalable approach for efficient and high-quality personalized image generation. By caching a small number of reference image features from a subset of layers and a single timestep of the pretrained diffusion denoiser, DreamCache enables dynamic modulation of the generated image features through lightweight, trained conditioning adapters. DreamCache achieves state-of-the-art image and text alignment, utilizing an order of magnitude fewer extra parameters, and is both more computationally effective and versatile than existing models.

Luca Savant Aira, Diego Valsesia, Andrea Bordone Molini et al.

Multi-image super-resolution (MISR) allows to increase the spatial resolution of a low-resolution (LR) acquisition by combining multiple images carrying complementary information in the form of sub-pixel offsets in the scene sampling, and can be significantly more effective than its single-image counterpart. Its main difficulty lies in accurately registering and fusing the multi-image information. Currently studied settings, such as burst photography, typically involve assumptions of small geometric disparity between the LR images and rely on optical flow for image registration. We study a MISR method that can increase the resolution of sets of images acquired with arbitrary, and potentially wildly different, camera positions and orientations, generalizing the currently studied MISR settings. Our proposed model, called EpiMISR, moves away from optical flow and explicitly uses the epipolar geometry of the acquisition process, together with transformer-based processing of radiance feature fields to substantially improve over state-of-the-art MISR methods in presence of large disparities in the LR images.

Ziyao Yi, Diego Valsesia, Tiziano Bianchi et al.

The rise of portable Lidar instruments, including their adoption in smartphones, opens the door to novel computational imaging techniques. Being an active sensing instrument, Lidar can provide complementary data to passive optical sensors, particularly in situations like low-light imaging where motion blur can affect photos. In this paper, we study if the depth information provided by mobile Lidar sensors is useful for the task of image deblurring and how to integrate it with a general approach that transforms any state-of-the-art neural deblurring model into a depth-aware one. To achieve this, we developed a universal adapter structure that efficiently preprocesses the depth information to modulate image features with depth features. Additionally, we applied a continual learning strategy to pretrained encoder-decoder models, enabling them to incorporate depth information as an additional input with minimal extra data requirements. We demonstrate that utilizing true depth information can significantly boost the effectiveness of deblurring algorithms, as validated on a dataset with real-world depth data captured by a smartphone Lidar.

Davide Piccinini, Diego Valsesia, Enrico Magli

Hyperspectral imagers on satellites obtain the fine spectral signatures essential for distinguishing one material from another at the expense of limited spatial resolution. Enhancing the latter is thus a desirable preprocessing step in order to further improve the detection capabilities offered by hyperspectral images on downstream tasks. At the same time, there is a growing interest towards deploying inference methods directly onboard of satellites, which calls for lightweight image super-resolution methods that can be run on the payload in real time. In this paper, we present a novel neural network design, called Deep Pushbroom Super-Resolution (DPSR) that matches the pushbroom acquisition of hyperspectral sensors by processing an image line by line in the along-track direction with a causal memory mechanism to exploit previously acquired lines. This design greatly limits memory requirements and computational complexity, achieving onboard real-time performance, i.e., the ability to super-resolve a line in the time it takes to acquire the next one, on low-power hardware. Experiments show that the quality of the super-resolved images is competitive or even outperforms state-of-the-art methods that are significantly more complex.

Gabriele Inzerillo, Diego Valsesia, Aniello Fiengo et al.

Change detection from satellite images typically incurs a delay ranging from several hours up to days because of latency in downlinking the acquired images and generating orthorectified image products at the ground stations; this may preclude real- or near real-time applications. To overcome this limitation, we propose shifting the entire change detection workflow onboard satellites. This requires to simultaneously solve challenges in data storage, image registration and change detection with a strict complexity constraint. In this paper, we present a novel and efficient framework for onboard change detection that addresses the aforementioned challenges in an end-to-end fashion with a deep neural network composed of three interlinked submodules: (1) image compression, tailored to minimize onboard data storage resources; (2) lightweight co-registration of non-orthorectified multi-temporal image pairs; and (3) a novel temporally-invariant and computationally efficient change detection model. This is the first approach in the literature combining all these tasks in a single end-to-end framework with the constraints dictated by onboard processing. Experimental results compare each submodule with the current state-of-the-art, and evaluate the performance of the overall integrated system in realistic setting on low-power hardware. Compelling change detection results are obtained in terms of F1 score as a function of compression rate, sustaining a throughput of 0.7 Mpixel/s on a 15W accelerator.

Antonio Montanaro, Diego Valsesia, Giulia Fracastoro et al.

Semi-supervised learning techniques are gaining popularity due to their capability of building models that are effective, even when scarce amounts of labeled data are available. In this paper, we present a framework and specific tasks for self-supervised pretraining of \textit{multichannel} models, such as the fusion of multispectral and synthetic aperture radar images. We show that the proposed self-supervised approach is highly effective at learning features that correlate with the labels for land cover classification. This is enabled by an explicit design of pretraining tasks which promotes bridging the gaps between sensing modalities and exploiting the spectral characteristics of the input. In a semi-supervised setting, when limited labels are available, using the proposed self-supervised pretraining, followed by supervised finetuning for land cover classification with SAR and multispectral data, outperforms conventional approaches such as purely supervised learning, initialization from training on ImageNet and other recent self-supervised approaches.

Diego Valsesia, Enrico Magli

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.

Antonio Alliegro, Diego Valsesia, Giulia Fracastoro et al.

In this paper, we present a deep learning model that exploits the power of self-supervision to perform 3D point cloud completion, estimating the missing part and a context region around it. Local and global information are encoded in a combined embedding. A denoising pretext task provides the network with the needed local cues, decoupled from the high-level semantics and naturally shared over multiple classes. On the other hand, contrastive learning maximizes the agreement between variants of the same shape with different missing portions, thus producing a representation which captures the global appearance of the shape. The combined embedding inherits category-agnostic properties from the chosen pretext tasks. Differently from existing approaches, this allows to better generalize the completion properties to new categories unseen at training time. Moreover, while decoding the obtained joint representation, we better blend the reconstructed missing part with the partial shape by paying attention to its known surrounding region and reconstructing this frame as auxiliary objective. Our extensive experiments and detailed ablation on the ShapeNet dataset show the effectiveness of each part of the method with new state of the art results. Our quantitative and qualitative analysis confirms how our approach is able to work on novel categories without relying neither on classification and shape symmetry priors, nor on adversarial training procedures.

Diego Valsesia, Giulia Fracastoro, Enrico Magli

Graph neural networks have become a staple in problems addressing learning and analysis of data defined over graphs. However, several results suggest an inherent difficulty in extracting better performance by increasing the number of layers. Recent works attribute this to a phenomenon peculiar to the extraction of node features in graph-based tasks, i.e., the need to consider multiple neighborhood sizes at the same time and adaptively tune them. In this paper, we investigate the recently proposed randomly wired architectures in the context of graph neural networks. Instead of building deeper networks by stacking many layers, we prove that employing a randomly-wired architecture can be a more effective way to increase the capacity of the network and obtain richer representations. We show that such architectures behave like an ensemble of paths, which are able to merge contributions from receptive fields of varied size. Moreover, these receptive fields can also be modulated to be wider or narrower through the trainable weights over the paths. We also provide extensive experimental evidence of the superior performance of randomly wired architectures over multiple tasks and four graph convolution definitions, using recent benchmarking frameworks that addresses the reliability of previous testing methodologies.

Giulia Fracastoro, Enrico Magli, Giovanni Poggi et al.

Synthetic aperture radar (SAR) images are affected by a spatially-correlated and signal-dependent noise called speckle, which is very severe and may hinder image exploitation. Despeckling is an important task that aims at removing such noise, so as to improve the accuracy of all downstream image processing tasks. The first despeckling methods date back to the 1970's, and several model-based algorithms have been developed in the subsequent years. The field has received growing attention, sparkled by the availability of powerful deep learning models that have yielded excellent performance for inverse problems in image processing. This paper surveys the literature on deep learning methods applied to SAR despeckling, covering both the supervised and the more recent self-supervised approaches. We provide a critical analysis of existing methods with the objective to recognize the most promising research lines, to identify the factors that have limited the success of deep models, and to propose ways forward in an attempt to fully exploit the potential of deep learning for SAR despeckling.

Francesca Pistilli, Giulia Fracastoro, Diego Valsesia et al.

Point clouds are an increasingly relevant data type but they are often corrupted by noise. We propose a deep neural network based on graph-convolutional layers that can elegantly deal with the permutation-invariance problem encountered by learning-based point cloud processing methods. The network is fully-convolutional and can build complex hierarchies of features by dynamically constructing neighborhood graphs from similarity among the high-dimensional feature representations of the points. When coupled with a loss promoting proximity to the ideal surface, the proposed approach significantly outperforms state-of-the-art methods on a variety of metrics. In particular, it is able to improve in terms of Chamfer measure and of quality of the surface normals that can be estimated from the denoised data. We also show that it is especially robust both at high noise levels and in presence of structured noise such as the one encountered in real LiDAR scans.

Andrea Bordone Molini, Diego Valsesia, Giulia Fracastoro et al.

Information extraction from synthetic aperture radar (SAR) images is heavily impaired by speckle noise, hence despeckling is a crucial preliminary step in scene analysis algorithms. The recent success of deep learning envisions a new generation of despeckling techniques that could outperform classical model-based methods. However, current deep learning approaches to despeckling require supervision for training, whereas clean SAR images are impossible to obtain. In the literature, this issue is tackled by resorting to either synthetically speckled optical images, which exhibit different properties with respect to true SAR images, or multi-temporal SAR images, which are difficult to acquire or fuse accurately. In this paper, inspired by recent works on blind-spot denoising networks, we propose a self-supervised Bayesian despeckling method. The proposed method is trained employing only noisy SAR images and can therefore learn features of real SAR images rather than synthetic data. Experiments show that the performance of the proposed approach is very close to the supervised training approach on synthetic data and superior on real data in both quantitative and visual assessments.

Andrea Bordone Molini, Diego Valsesia, Giulia Fracastoro et al.

SAR despeckling is a problem of paramount importance in remote sensing, since it represents the first step of many scene analysis algorithms. Recently, deep learning techniques have outperformed classical model-based despeckling algorithms. However, such methods require clean ground truth images for training, thus resorting to synthetically speckled optical images since clean SAR images cannot be acquired. In this paper, inspired by recent works on blind-spot denoising networks, we propose a self-supervised Bayesian despeckling method. The proposed method is trained employing only noisy images and can therefore learn features of real SAR images rather than synthetic data. We show that the performance of the proposed network is very close to the supervised training approach on synthetic data and competitive on real data.

Andrea Bordone Molini, Diego Valsesia, Giulia Fracastoro et al.

Deep learning methods for super-resolution of a remote sensing scene from multiple unregistered low-resolution images have recently gained attention thanks to a challenge proposed by the European Space Agency. This paper presents an evolution of the winner of the challenge, showing how incorporating non-local information in a convolutional neural network allows to exploit self-similar patterns that provide enhanced regularization of the super-resolution problem. Experiments on the dataset of the challenge show improved performance over the state-of-the-art, which does not exploit non-local information.

Diego Valsesia, Sophie Marie Fosson, Chiara Ravazzi et al.

Embeddings provide compact representations of signals in order to perform efficient inference in a wide variety of tasks. In particular, random projections are common tools to construct Euclidean distance-preserving embeddings, while hashing techniques are extensively used to embed set-similarity metrics, such as the Jaccard coefficient. In this letter, we theoretically prove that a class of random projections based on sparse matrices, called SparseHash, can preserve the Jaccard coefficient between the supports of sparse signals, which can be used to estimate set similarities. Moreover, besides the analysis, we provide an efficient implementation and we test the performance in several numerical experiments, both on synthetic and real datasets.

Diego Valsesia, Giulia Fracastoro, Enrico Magli

Non-local self-similarity is well-known to be an effective prior for the image denoising problem. However, little work has been done to incorporate it in convolutional neural networks, which surpass non-local model-based methods despite only exploiting local information. In this paper, we propose a novel end-to-end trainable neural network architecture employing layers based on graph convolution operations, thereby creating neurons with non-local receptive fields. The graph convolution operation generalizes the classic convolution to arbitrary graphs. In this work, the graph is dynamically computed from similarities among the hidden features of the network, so that the powerful representation learning capabilities of the network are exploited to uncover self-similar patterns. We introduce a lightweight Edge-Conditioned Convolution which addresses vanishing gradient and over-parameterization issues of this particular graph convolution. Extensive experiments show state-of-the-art performance with improved qualitative and quantitative results on both synthetic Gaussian noise and real noise.

Andrea Bordone Molini, Diego Valsesia, Giulia Fracastoro et al.

Recently, convolutional neural networks (CNN) have been successfully applied to many remote sensing problems. However, deep learning techniques for multi-image super-resolution from multitemporal unregistered imagery have received little attention so far. This work proposes a novel CNN-based technique that exploits both spatial and temporal correlations to combine multiple images. This novel framework integrates the spatial registration task directly inside the CNN, and allows to exploit the representation learning capabilities of the network to enhance registration accuracy. The entire super-resolution process relies on a single CNN with three main stages: shared 2D convolutions to extract high-dimensional features from the input images; a subnetwork proposing registration filters derived from the high-dimensional feature representations; 3D convolutions for slow fusion of the features from multiple images. The whole network can be trained end-to-end to recover a single high resolution image from multiple unregistered low resolution images. The method presented in this paper is the winner of the PROBA-V super-resolution challenge issued by the European Space Agency.

Diego Valsesia, Enrico Magli

Compression of hyperspectral images onboard of spacecrafts is a tradeoff between the limited computational resources and the ever-growing spatial and spectral resolution of the optical instruments. As such, it requires low-complexity algorithms with good rate-distortion performance and high throughput. In recent years, the Consultative Committee for Space Data Systems (CCSDS) has focused on lossless and near-lossless compression approaches based on predictive coding, resulting in the recently published CCSDS 123.0-B-2 recommended standard. While the in-loop reconstruction of quantized prediction residuals provides excellent rate-distortion performance for the near-lossless operating mode, it significantly constrains the achievable throughput due to data dependencies. In this paper, we study the performance of a faster method based on prequantization of the image followed by a lossless predictive compressor. While this is well known to be suboptimal, one can exploit powerful signal models to reconstruct the image at the ground segment, recovering part of the suboptimality. In particular, we show that convolutional neural networks can be used for this task and that they can recover the whole SNR drop incurred at a bitrate of 2 bits per pixel.

Diego Valsesia, Giulia Fracastoro, Enrico Magli

Recovering an image from a noisy observation is a key problem in signal processing. Recently, it has been shown that data-driven approaches employing convolutional neural networks can outperform classical model-based techniques, because they can capture more powerful and discriminative features. However, since these methods are based on convolutional operations, they are only capable of exploiting local similarities without taking into account non-local self-similarities. In this paper we propose a convolutional neural network that employs graph-convolutional layers in order to exploit both local and non-local similarities. The graph-convolutional layers dynamically construct neighborhoods in the feature space to detect latent correlations in the feature maps produced by the hidden layers. The experimental results show that the proposed architecture outperforms classical convolutional neural networks for the denoising task.

Diego Valsesia, Enrico Magli

We use some of the largest order statistics of the random projections of a reference signal to construct a binary embedding that is adapted to signals correlated with such signal. The embedding is characterized from the analytical standpoint and shown to provide improved performance on tasks such as classification in a reduced-dimensionality space.

Giulio Coluccia, Diego Valsesia, Enrico Magli

In this paper we address the problem of visual quality of images reconstructed from block-wise random projections. Independent reconstruction of the blocks can severely affect visual quality, by displaying artifacts along block borders. We propose a method to enforce smoothness across block borders by modifying the sensing and reconstruction process so as to employ partially overlapping blocks. The proposed algorithm accomplishes this by computing a fast preview from the blocks, whose purpose is twofold. On one hand, it allows to enforce a set of constraints to drive the reconstruction algorithm towards a smooth solution, imposing the similarity of block borders. On the other hand, the preview is used as a predictor of the entire block, allowing to recover the prediction error, only. The quality improvement over the result of independent reconstruction can be easily assessed both visually and in terms of PSNR and SSIM index.

Diego Valsesia, Enrico Magli

Compressive imaging is an emerging application of compressed sensing, devoted to acquisition, encoding and reconstruction of images using random projections as measurements. In this paper we propose a novel method to provide a scalable encoding of an image acquired by means of compressed sensing techniques. Two bit-streams are generated to provide two distinct quality levels: a low-resolution base layer and full-resolution enhancement layer. In the proposed method we exploit a fast preview of the image at the encoder in order to perform inter-layer prediction and encode the prediction residuals only. The proposed method successfully provides resolution and quality scalability with modest complexity and it provides gains in the quality of the reconstructed images with respect to separate encoding of the quality layers. Remarkably, we also show that the scheme can also provide significant gains with respect to a direct, non-scalable system, thus accomplishing two features at once: scalability and improved reconstruction performance.