32 accepted papers
Samples of brain signals collected by EEG sensors have inherent anti-correlations that are well modeled by negative edges in a finite graph. To differentiate epilepsy patients from healthy subjects using collected EEG signals, we build lightweight and interpretable transformer-like neural nets by…
To forecast traffic with both spatial and temporal dimensions, we unroll a mixed-graph-based optimization algorithm into a lightweight and interpretable transformer-like neural net. Specifically, we construct two graphs: an undirected graph $\mathcal{G}^u$ capturing spatial correlations across geogr…
Signed graphs are equipped with both positive and negative edge weights, encoding pairwise correlations as well as anti-correlations in data. A balanced signed graph has no cycles of odd number of negative edges. Laplacian of a balanced signed graph has eigenvectors that map simply to ones in a simi…
We build interpretable and lightweight transformer-like neural networks by unrolling iterative optimization algorithms that minimize graph smoothness priors---the quadratic graph Laplacian regularizer (GLR) and the $\ell_1$-norm graph total variation (GTV)---subject to an interpolation constraint. T…
A basic premise in graph signal processing (GSP) is the existence of an underlying graph capturing pairwise similarities/correlations between nodes, using which graph filtering tasks such as denoising and interpolation are performed. In practice, node-to-node similarities often evolve over time, and…
A noise-corrupted image often requires interpolation. Given a linear denoiser and a linear interpolator, when should the operations be independently executed in separate steps, and when should they be combined and jointly optimized? We study joint denoising / interpolation of images from a mixed gra…
We revisit the well-studied image segmentation problem from a soft labeling perspective: instead of estimating integer labels per pixel indicating a finite set of classes, each pixel is assigned a real number that conveys the level of uncertainty in the estimated class label. Soft labels are useful,…
We extend a previous study on 3D point cloud attribute compression scheme that uses a volumetric approach: given a target volumetric attribute function f : ℝ <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> ↦ ℝ, we quantize and encode parameters…
Graph sampling is the problem of choosing a node subset via sampling matrix H ∈ {0, 1} <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">K×N</sup> to collect samples y = Hx ∈ℝ <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.…
During the Covid-19 pandemic, like the vast majority of countries in the world, Canada was under government-mandated lockdown, creating unprecedented challenges for the higher education system. This has exacerbated the problem of gender and ethnic inequalities in the STEM field due to the sudden dis…
A graph convolutional network (GCN) employs a graph filtering kernel tailored for data with irregular structures. However, simply stacking more GCN layers does not improve performance; instead, the output converges to an uninformative low-dimensional subspace, where the convergence rate is character…
We study 3D point cloud attribute compression using a volumetric approach: given a target volumetric attribute function f : ℝ <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> → ℝ, we quantize and encode parameter vector θ that characterizes f at…
We study the problem of efficiently summarizing a short video into several keyframes, leveraging recent progress in fast graph sampling. Specifically, we first construct a similarity path graph (SPG) G, represented by graph Laplacian matrix L, where the similarities between adjacent frames are encod…
In graph signal processing (GSP), an appropriate underlying graph encodes pairwise (anti-)correlations of targeted discrete signals as edge weights. However, existing fast graph sampling schemes are designed and tested for positive graphs describing only positive correlations. In this paper, we show…
Manifold landmarking is the problem of selecting a subset of discrete locations on a continuous manifold for label assignment, in order to reduce interpolation error of subsequent semi-supervised learning. In this paper, we select landmarks to minimize the condition number (λ <inf xmlns:mml="http://…
Learning a suitable graph is an important precursor to many graph signal processing (GSP) pipelines, such as graph signal compression and denoising. Previous graph learning algorithms either i) make assumptions on graph connectivity (e.g., graph sparsity), or ii) make edge weight assumptions such as…
While deep learning (DL) architectures like convolutional neural networks (CNNs) have enabled effective solutions in image denoising, in general their implementations overly rely on training data, lack interpretability, and require tuning of a large parameter set. In this paper, we combine classical…
We propose a general projection-free metric learning framework, where the minimization objective ${\min _{{\mathbf{M}} \in \mathcal{S}}}Q({\mathbf{M}})$ is a convex differentiable function of the metric matrix M, and M resides in the set S of generalized graph Laplacian matrices for connected graphs…
While convolutional neural nets (CNNs) have achieved remarkable performance for a wide range of inverse imaging applications, the filter coefficients are computed in a purely data-driven manner and are not explainable. Inspired by an analytically derived CNN by Hadji et al., in this paper we constru…
Conventional video coding schemes employ a hybrid motion prediction / residual transform coding paradigm, which only exploits redundancy in individual pairs of video frames for compression gain. However, rigid geometric structures in 3D space—e.g., a building in a scene’s background—persist across t…
High-definition 360 videos encoded in fine quality are typically too large in size to stream in its entirety over bandwidth (BW)-constrained networks. One popular remedy is to interactively extract and send a spatial sub-region corresponding to a viewer's current field-of-view (FoV) in a head-mounte…
3D point clouds acquired by low-cost sensors are often in lower spatial resolutions than desired for rendering images on high-resolution displays. In this paper, we propose a fast super-resolution (SR) algorithm for color 3D point clouds. We first populate a target low-res point cloud with added int…
With growing interest in data-driven classification, deep learning is now prevalent due to its ability to learn feature mapping functions solely from data. For very small training sets, however, deep learning, even with traditional regularization techniques, often overfits, resulting in sub-par clas…
Graph sampling with independent noise towards minimum mean square error (MMSE) leads to the known A-optimality criterion, which is computation-intensive to evaluate and NP-hard to optimize. In this paper, we propose a new low-complexity sampling strategy based on Neumann series that circumvents larg…
Graph sampling with noise is a fundamental problem in graph signal processing (GSP). Previous works assume an unbiased least square (LS) signal reconstruction scheme and select samples greedily via expensive extreme eigenvector computation. A popular biased scheme using graph Laplacian regularizatio…
Blind image deblurring, i.e., deblurring without knowledge of the blur kernel, is a highly ill-posed problem. The problem can be solved in two parts: i) estimate a blur kernel from the blurry image, and ii) given estimated blur kernel, de-convolve blurry input to restore the target image. In this pa…
Light field data captured by a lenslet-based image sensor is typically demosaicked, aligned and rearranged into a series of sub-aperture (viewpoint) images, before a disparity-compensated coding scheme is employed for compression. In this paper, we focus on the problem of soft decoding of block-base…
The observation of frequency folding in graph spectrum during down-sampling for signals on bipartite graphs-analogous to the same phenomenon in Fourier domain for regularly sampled signals-has led to the development of critically sampled wavelet filterbanks such as GraphBior. However, typical graph-…
Instead of lossily coding depth images resulting in undesirable geometric distortion, graph-based representation (GBR) describes disparity information as a graph with a controllable accuracy. In this paper, we propose a more compact graphical representation called GBR-plus to code both disparity and…
Social media sites like Facebook are obligated to store all photos uploaded by an ever growing user base-which translates to an increasingly expensive storage cost-but only a fraction of uploaded images are revisited thereafter. In this paper, we propose a cloud storage system that trades off comput…
Images and videos are often captured in poor light conditions, resulting in low-contrast images that are corrupted by acquisition noise. To recreate a high-quality image for visual observation, the captured image must be denoised and contrastenhanced. Conventional methods perform these two tasks in…
Image denoising is an under-determined problem, and hence it is important to define appropriate image priors for regularization. One recent popular prior is the graph Laplacian regularizer, where a given pixel patch is assumed to be smooth in the graph-signal domain. The strength and direction of th…