arXiv subjects

Suren Jayasuriya

Publications and source records attributed to Suren Jayasuriya.

35 records · Page 2Linked to original sources

arXiv2021

Restoring degraded speech via a modified diffusion model

There are many deterministic mathematical operations (e.g. compression, clipping, downsampling) that degrade speech quality considerably. In this paper we introduce a neural network architecture, based on a modification of the DiffWave model, that aims to restore the original speech signal. DiffWave, a recently published diffusion-based vocoder, has shown state-of-the-art synthesized speech quality and relatively shorter waveform generation times, with only a small set of parameters. We replace the mel-spectrum upsampler in DiffWave with a deep CNN upsampler, which is trained to alter the degraded speech mel-spectrum to match that of the original speech. The model is trained using the original speech waveform, but conditioned on the degraded speech mel-spectrum. Post-training, only the degraded mel-spectrum is used as input and the model generates an estimate of the original speech. Our model results in improved speech quality (original DiffWave model as baseline) on several different experiments. These include improving the quality of speech degraded by LPC-10 compression, AMR-NB compression, and signal clipping. Compared to the original DiffWave architecture, our scheme achieves better performance on several objective perceptual metrics and in subjective comparisons. Improvements over baseline are further amplified in a out-of-corpus evaluation setting.

cs.SD↗

arXiv2021

Deep Camera Obscura: An Image Restoration Pipeline for Lensless Pinhole Photography

The lensless pinhole camera is perhaps the earliest and simplest form of an imaging system using only a pinhole-sized aperture in place of a lens. They can capture an infinite depth-of-field and offer greater freedom from optical distortion over their lens-based counterparts. However, the inherent limitations of a pinhole system result in lower sharpness from blur caused by optical diffraction and higher noise levels due to low light throughput of the small aperture, requiring very long exposure times to capture well-exposed images. In this paper, we explore an image restoration pipeline using deep learning and domain-knowledge of the pinhole system to enhance the pinhole image quality through a joint denoise and deblur approach. Our approach allows for more practical exposure times for hand-held photography and provides higher image quality, making it more suitable for daily photography compared to other lensless cameras while keeping size and cost low. This opens up the potential of pinhole cameras to be used in smaller devices, such as smartphones.

cs.CV↗

arXiv2021

Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fields

Reconstructing dynamic, time-varying scenes with computed tomography (4D-CT) is a challenging and ill-posed problem common to industrial and medical settings. Existing 4D-CT reconstructions are designed for sparse sampling schemes that require fast CT scanners to capture multiple, rapid revolutions around the scene in order to generate high quality results. However, if the scene is moving too fast, then the sampling occurs along a limited view and is difficult to reconstruct due to spatiotemporal ambiguities. In this work, we design a reconstruction pipeline using implicit neural representations coupled with a novel parametric motion field warping to perform limited view 4D-CT reconstruction of rapidly deforming scenes. Importantly, we utilize a differentiable analysis-by-synthesis approach to compare with captured x-ray sinogram data in a self-supervised fashion. Thus, our resulting optimization method requires no training data to reconstruct the scene. We demonstrate that our proposed system robustly reconstructs scenes containing deformable and periodic motion and validate against state-of-the-art baselines. Further, we demonstrate an ability to reconstruct continuous spatiotemporal representations of our scenes and upsample them to arbitrary volumes and frame rates post-optimization. This research opens a new avenue for implicit neural representations in computed tomography reconstruction in general.

eess.IV↗

arXiv2020

Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion Model

Hyperspectral unmixing is an important remote sensing task with applications including material identification and analysis. Characteristic spectral features make many pure materials identifiable from their visible-to-infrared spectra, but quantifying their presence within a mixture is a challenging task due to nonlinearities and factors of variation. In this paper, spectral variation is considered from a physics-based approach and incorporated into an end-to-end spectral unmixing algorithm via differentiable programming. The dispersion model is introduced to simulate realistic spectral variation, and an efficient method to fit the parameters is presented. Then, this dispersion model is utilized as a generative model within an analysis-by-synthesis spectral unmixing algorithm. Further, a technique for inverse rendering using a convolutional neural network to predict parameters of the generative model is introduced to enhance performance and speed when training data is available. Results achieve state-of-the-art on both infrared and visible-to-near-infrared (VNIR) datasets, and show promise for the synergy between physics-based models and deep learning in hyperspectral unmixing in the future.

cs.CV↗

arXiv2019

Thresholded Non-Uniform Fourier Frame-Based Reconstruction for Stripmap SAR

Fourier domain methods are fast algorithms for SAR imaging. They typically involve an interpolation in the frequency domain to re-grid non-uniform data so inverse fast Fourier transforms can be performed. In this paper, we apply a frame reconstruction algorithm, extending the non-uniform fast Fourier transform, to stripmap SAR data. Further, we present an improved thresholded frame reconstruction algorithm for robust performance and improved computational efficiency. We demonstrate compelling results on real stripmap SAR data.

eess.SP↗

arXiv2019

Coupling Rendering and Generative Adversarial Networks for Artificial SAS Image Generation

Acquisition of Synthetic Aperture Sonar (SAS) datasets is bottlenecked by the costly deployment of SAS imaging systems, and even when data acquisition is possible,the data is often skewed towards containing barren seafloor rather than objects of interest. We present a novel pipeline, called SAS GAN, which couples an optical renderer with a generative adversarial network (GAN) to synthesize realistic SAS images of targets on the seafloor. This coupling enables high levels of SAS image realism while enabling control over image geometry and parameters. We demonstrate qualitative results by presenting examples of images created with our pipeline. We also present quantitative results through the use of t-SNE and the Fréchet Inception Distance to argue that our generated SAS imagery potentially augments SAS datasets more effectively than an off-the-shelf GAN.

eess.IV↗

arXiv2019

Adaptive Lighting for Data-Driven Non-Line-of-Sight 3D Localization and Object Identification

Non-line-of-sight (NLOS) imaging of objects not visible to either the camera or illumination source is a challenging task with vital applications including surveillance and robotics. Recent NLOS reconstruction advances have been achieved using time-resolved measurements which requires expensive and specialized detectors and laser sources. In contrast, we propose a data-driven approach for NLOS 3D localization and object identification requiring only a conventional camera and projector. To generalize to complex line-of-sight (LOS) scenes with non-planar surfaces and occlusions, we introduce an adaptive lighting algorithm. This algorithm, based on radiosity, identifies and illuminates scene patches in the LOS which most contribute to the NLOS light paths, and can factor in system power constraints. We achieve an average identification of 87.1% object identification for four classes of objects, and average localization of the NLOS object's centroid with a mean-squared error (MSE) of 1.97 cm in the occluded region for real data taken from a hardware prototype. These results demonstrate the advantage of combining the physics of light transport with active illumination for data-driven NLOS imaging.

eess.IV↗

arXiv2019

Non-Parametric Priors For Generative Adversarial Networks

The advent of generative adversarial networks (GAN) has enabled new capabilities in synthesis, interpolation, and data augmentation heretofore considered very challenging. However, one of the common assumptions in most GAN architectures is the assumption of simple parametric latent-space distributions. While easy to implement, a simple latent-space distribution can be problematic for uses such as interpolation. This is due to distributional mismatches when samples are interpolated in the latent space. We present a straightforward formalization of this problem; using basic results from probability theory and off-the-shelf-optimization tools, we develop ways to arrive at appropriate non-parametric priors. The obtained prior exhibits unusual qualitative properties in terms of its shape, and quantitative benefits in terms of lower divergence with its mid-point distribution. We demonstrate that our designed prior helps improve image generation along any Euclidean straight line during interpolation, both qualitatively and quantitatively, without any additional training or architectural modifications. The proposed formulation is quite flexible, paving the way to impose newer constraints on the latent-space statistics.

cs.CV↗

arXiv2018

CS-VQA: Visual Question Answering with Compressively Sensed Images

Visual Question Answering (VQA) is a complex semantic task requiring both natural language processing and visual recognition. In this paper, we explore whether VQA is solvable when images are captured in a sub-Nyquist compressive paradigm. We develop a series of deep-network architectures that exploit available compressive data to increasing degrees of accuracy, and show that VQA is indeed solvable in the compressed domain. Our results show that there is nominal degradation in VQA performance when using compressive measurements, but that accuracy can be recovered when VQA pipelines are used in conjunction with state-of-the-art deep neural networks for CS reconstruction. The results presented yield important implications for resource-constrained VQA applications.

cs.CV↗

arXiv2018

EVA$^2$: Exploiting Temporal Redundancy in Live Computer Vision

Hardware support for deep convolutional neural networks (CNNs) is critical to advanced computer vision in mobile and embedded devices. Current designs, however, accelerate generic CNNs; they do not exploit the unique characteristics of real-time vision. We propose to use the temporal redundancy in natural video to avoid unnecessary computation on most frames. A new algorithm, activation motion compensation, detects changes in the visual input and incrementally updates a previously-computed output. The technique takes inspiration from video compression and applies well-known motion estimation techniques to adapt to visual changes. We use an adaptive key frame rate to control the trade-off between efficiency and vision quality as the input changes. We implement the technique in hardware as an extension to existing state-of-the-art CNN accelerator designs. The new unit reduces the average energy per frame by 54.2%, 61.7%, and 87.6% for three CNNs with less than 1% loss in vision accuracy.

cs.CV↗

arXiv2018

Compressive Light Field Reconstructions using Deep Learning

Light field imaging is limited in its computational processing demands of high sampling for both spatial and angular dimensions. Single-shot light field cameras sacrifice spatial resolution to sample angular viewpoints, typically by multiplexing incoming rays onto a 2D sensor array. While this resolution can be recovered using compressive sensing, these iterative solutions are slow in processing a light field. We present a deep learning approach using a new, two branch network architecture, consisting jointly of an autoencoder and a 4D CNN, to recover a high resolution 4D light field from a single coded 2D image. This network decreases reconstruction time significantly while achieving average PSNR values of 26-32 dB on a variety of light fields. In particular, reconstruction time is decreased from 35 minutes to 6.7 minutes as compared to the dictionary method for equivalent visual quality. These reconstructions are performed at small sampling/compression ratios as low as 8%, allowing for cheaper coded light field cameras. We test our network reconstructions on synthetic light fields, simulated coded measurements of real light fields captured from a Lytro Illum camera, and real coded images from a custom CMOS diffractive light field camera. The combination of compressive light field capture with deep learning allows the potential for real-time light field video acquisition systems in the future.

cs.CV↗

arXiv2017

Reconfiguring the Imaging Pipeline for Computer Vision

Advancements in deep learning have ignited an explosion of research on efficient hardware for embedded computer vision. Hardware vision acceleration, however, does not address the cost of capturing and processing the image data that feeds these algorithms. We examine the role of the image signal processing (ISP) pipeline in computer vision to identify opportunities to reduce computation and save energy. The key insight is that imaging pipelines should be designed to be configurable: to switch between a traditional photography mode and a low-power vision mode that produces lower-quality image data suitable only for computer vision. We use eight computer vision algorithms and a reversible pipeline simulation tool to study the imaging system's impact on vision performance. For both CNN-based and classical vision algorithms, we observe that only two ISP stages, demosaicing and gamma compression, are critical for task performance. We propose a new image sensor design that can compensate for skipping these stages. The sensor design features an adjustable resolution and tunable analog-to-digital converters (ADCs). Our proposed imaging system's vision mode disables the ISP entirely and configures the sensor to produce subsampled, lower-precision image data. This vision mode can save ~75% of the average energy of a baseline photography mode while having only a small impact on vision task accuracy.

cs.CV↗

arXiv2016

Deep Learning with Energy-efficient Binary Gradient Cameras

Power consumption is a critical factor for the deployment of embedded computer vision systems. We explore the use of computational cameras that directly output binary gradient images to reduce the portion of the power consumption allocated to image sensing. We survey the accuracy of binary gradient cameras on a number of computer vision tasks using deep learning. These include object recognition, head pose regression, face detection, and gesture recognition. We show that, for certain applications, accuracy can be on par or even better than what can be achieved on traditional images. We are also the first to recover intensity information from binary spatial gradient images--useful for applications with a human observer in the loop, such as surveillance. Our results, which we validate with a prototype binary gradient camera, point to the potential of gradient-based computer vision systems.

cs.CV↗

arXiv2016

ASP Vision: Optically Computing the First Layer of Convolutional Neural Networks using Angle Sensitive Pixels

Deep learning using convolutional neural networks (CNNs) is quickly becoming the state-of-the-art for challenging computer vision applications. However, deep learning's power consumption and bandwidth requirements currently limit its application in embedded and mobile systems with tight energy budgets. In this paper, we explore the energy savings of optically computing the first layer of CNNs. To do so, we utilize bio-inspired Angle Sensitive Pixels (ASPs), custom CMOS diffractive image sensors which act similar to Gabor filter banks in the V1 layer of the human visual cortex. ASPs replace both image sensing and the first layer of a conventional CNN by directly performing optical edge filtering, saving sensing energy, data bandwidth, and CNN FLOPS to compute. Our experimental results (both on synthetic data and a hardware prototype) for a variety of vision tasks such as digit recognition, object recognition, and face identification demonstrate using ASPs while achieving similar performance compared to traditional deep learning pipelines.

cs.CV↗

arXiv2015

Depth Fields: Extending Light Field Techniques to Time-of-Flight Imaging

A variety of techniques such as light field, structured illumination, and time-of-flight (TOF) are commonly used for depth acquisition in consumer imaging, robotics and many other applications. Unfortunately, each technique suffers from its individual limitations preventing robust depth sensing. In this paper, we explore the strengths and weaknesses of combining light field and time-of-flight imaging, particularly the feasibility of an on-chip implementation as a single hybrid depth sensor. We refer to this combination as depth field imaging. Depth fields combine light field advantages such as synthetic aperture refocusing with TOF imaging advantages such as high depth resolution and coded signal processing to resolve multipath interference. We show applications including synthesizing virtual apertures for TOF imaging, improved depth mapping through partial and scattering occluders, and single frequency TOF phase unwrapping. Utilizing space, angle, and temporal coding, depth fields can improve depth sensing in the wild and generate new insights into the dimensions of light's plenoptic function.

cs.CV↗

arXiv2015

Frequency Domain TOF: Encoding Object Depth in Modulation Frequency

Time of flight cameras may emerge as the 3-D sensor of choice. Today, time of flight sensors use phase-based sampling, where the phase delay between emitted and received, high-frequency signals encodes distance. In this paper, we present a new time of flight architecture that relies only on frequency---we refer to this technique as frequency-domain time of flight (FD-TOF). Inspired by optical coherence tomography (OCT), FD-TOF excels when frequency bandwidth is high. With the increasing frequency of TOF sensors, new challenges to time of flight sensing continue to emerge. At high frequencies, FD-TOF offers several potential benefits over phase-based time of flight methods.

cs.CV↗

arXiv2013

The inverse Erdos-Heilbronn Problem for restricted set addition in finite groups

We provide a survey of results concerning both the direct and inverse problems to the Cauchy-Davenport theorem and Erdos-Heilbronn problem in Additive Combinatorics. We prove a slight extension to an inverse theorem of Dias da Silva-Hamidoune in Z/pZ, and we present a counterexample to an open conjecture concerning the inverse Erdos-Heilbronn problem in nonabelian groups.

math.CO↗