Search Results for author: Ashok Veeraraghavan

Found 47 papers, 15 papers with code

3PointTM: Faster Measurement of High-Dimensional Transmission Matrices

no code implementations ECCV 2020 Yujun Chen, Manoj Kumar Sharma, Ashutosh Sabharwal, Ashok Veeraraghavan, Aswin C. Sankaranarayanan

A transmission matrix (TM) describes the linear relationship between input and output phasor fields when a coherent wave passes through a scattering medium.

Image Reconstruction Retrieval +1

FreeCam3D: Snapshot Structured Light 3D with Freely-Moving Cameras

no code implementations ECCV 2020 Yicheng Wu, Vivek Boominathan, Xuan Zhao, Jacob T. Robinson, Hiroshi Kawasaki, Aswin Sankaranarayanan, Ashok Veeraraghavan

The projected pattern can be observed in part or full by any camera, to reconstruct both the 3D map of the scene and the camera pose in the projector coordinates.

3D Reconstruction

Event-based Motion-Robust Accurate Shape Estimation for Mixed Reflectance Scenes

no code implementations16 Nov 2023 Aniket Dashpute, Jiazhang Wang, James Taylor, Oliver Cossairt, Ashok Veeraraghavan, Florian Willomitzer

In this paper, we present a novel event-based structured light system that enables fast 3D imaging of mixed reflectance scenes with high accuracy.

ISLAND: Informing Brightness and Surface Temperature Through a Land Cover-based Interpolator

no code implementations21 Sep 2023 Yuhao Liu, Pranavesh Panakkal, Sylvia Dee, Guha Balakrishnan, Jamie Padgett, Ashok Veeraraghavan

Our approach uses thermal infrared images from Landsat 8 (at 30 m resolution with 16-day revisit cycles) and the NLCD land cover dataset.

Blocking Time Series Analysis

CT Reconstruction from Few Planar X-rays with Application towards Low-resource Radiotherapy

1 code implementation4 Aug 2023 Yiran Sun, Tucker Netherton, Laurence Court, Ashok Veeraraghavan, Guha Balakrishnan

In this work, we propose a method to generate CT volumes from few (<5) planar X-ray observations using a prior data distribution, and perform the first evaluation of such a reconstruction algorithm for a clinical application: radiotherapy planning.

Anatomy SSIM

NeRT: Implicit Neural Representations for General Unsupervised Turbulence Mitigation

no code implementations1 Aug 2023 Weiyun Jiang, Vivek Boominathan, Ashok Veeraraghavan

The atmospheric and water turbulence mitigation problems have emerged as challenging inverse problems in computer vision and optics communities over the years.

Thermal Spread Functions (TSF): Physics-guided Material Classification

1 code implementation CVPR 2023 Aniket Dashpute, Vishwanath Saragadam, Emma Alexander, Florian Willomitzer, Aggelos Katsaggelos, Ashok Veeraraghavan, Oliver Cossairt

Our key observation is that the rate of heating and cooling of an object depends on the unique intrinsic properties of the material, namely the emissivity and diffusivity.

Classification Material Classification +1

Role of Transients in Two-Bounce Non-Line-of-Sight Imaging

no code implementations CVPR 2023 Siddharth Somasundaram, Akshat Dave, Connor Henley, Ashok Veeraraghavan, Ramesh Raskar

Specifically, we study how ToF information can reduce the number of measurements and spatial resolution needed for shape reconstruction.

Vocal Bursts Valence Prediction

ORCa: Glossy Objects As Radiance-Field Cameras

no code implementations CVPR 2023 Kushagra Tiwary, Akshat Dave, Nikhil Behari, Tzofi Klinghoffer, Ashok Veeraraghavan, Ramesh Raskar

By converting these objects into cameras, we can unlock exciting applications, including imaging beyond the camera's field-of-view and from seemingly impossible vantage points, e. g. from reflections on the human eye.

Novel View Synthesis

Foveated Thermal Computational Imaging in the Wild Using All-Silicon Meta-Optics

no code implementations13 Dec 2022 Vishwanath Saragadam, Zheyi Han, Vivek Boominathan, Luocheng Huang, Shiyu Tan, Johannes E. Fröch, Karl F. Böhringer, Richard G. Baraniuk, Arka Majumdar, Ashok Veeraraghavan

A computational backend then utilizes a deep image prior to separate the resultant multiplexed image or video into a foveated image consisting of a high-resolution center and a lower-resolution large field of view context.

ORCa: Glossy Objects as Radiance Field Cameras

1 code implementation8 Dec 2022 Kushagra Tiwary, Akshat Dave, Nikhil Behari, Tzofi Klinghoffer, Ashok Veeraraghavan, Ramesh Raskar

By converting these objects into cameras, we can unlock exciting applications, including imaging beyond the camera's field-of-view and from seemingly impossible vantage points, e. g. from reflections on the human eye.

Novel View Synthesis

Learning Phase Mask for Privacy-Preserving Passive Depth Estimation

no code implementations European Conference on Computer Vision (ECCV) 2022 Zaid Tasneem, Giovanni Milione, Yi-Hsuan Tsai, Xiang Yu, Ashok Veeraraghavan, Manmohan Chandraker, Francesco Pittaluga

With over a billion sold each year, cameras are not only becoming ubiquitous and omnipresent, but are driving progress in a wide range of applications such as augmented/virtual reality, robotics, surveillance, security, autonomous navigation and many others.

Autonomous Navigation Depth Estimation +2

PS$^2$F: Polarized Spiral Point Spread Function for Single-Shot 3D Sensing

no code implementations3 Jul 2022 Bhargav Ghanekar, Vishwanath Saragadam, Dushyant Mehra, Anna-Karin Gustavsson, Aswin Sankaranarayanan, Ashok Veeraraghavan

A special property of the phase mask used for generating the DHPSF is that a separation of the phase mask into two halves leads to a spatial separation of the two lobes.

Monocular Depth Estimation Super-Resolution

DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors

no code implementations7 Apr 2022 Vishwanath Saragadam, Randall Balestriero, Ashok Veeraraghavan, Richard G. Baraniuk

DeepTensor is a computationally efficient framework for low-rank decomposition of matrices and tensors using deep generative networks.

Hyperspectral Image Denoising Image Classification +2

PANDORA: Polarization-Aided Neural Decomposition Of Radiance

no code implementations25 Mar 2022 Akshat Dave, Yongyi Zhao, Ashok Veeraraghavan

Reconstructing an object's geometry and appearance from multiple images, also known as inverse rendering, is a fundamental problem in computer graphics and vision.

Inverse Rendering Novel View Synthesis

MINER: Multiscale Implicit Neural Representations

1 code implementation7 Feb 2022 Vishwanath Saragadam, Jasper Tan, Guha Balakrishnan, Richard G. Baraniuk, Ashok Veeraraghavan

We introduce a new neural signal model designed for efficient high-resolution representation of large-scale signals.

Image Reconstruction

Thermal Image Processing via Physics-Inspired Deep Networks

1 code implementation18 Aug 2021 Vishwanath Saragadam, Akshat Dave, Ashok Veeraraghavan, Richard Baraniuk

We introduce DeepIR, a new thermal image processing framework that combines physically accurate sensor modeling with deep network-based image representation.

Denoising Sensor Modeling +1

CodedStereo: Learned Phase Masks for Large Depth-of-field Stereo

no code implementations CVPR 2021 Shiyu Tan, Yicheng Wu, Shoou-I Yu, Ashok Veeraraghavan

Conventional stereo suffers from a fundamental trade-off between imaging volume and signal-to-noise ratio (SNR) -- due to the conflicting impact of aperture size on both these variables.

Disparity Estimation Image Reconstruction +1

High Resolution, Deep Imaging Using Confocal Time-of-flight Diffuse Optical Tomography

no code implementations27 Jan 2021 Yongyi Zhao, Ankit Raghuram, Hyun K. Kim, Andreas H. Hielscher, Jacob T. Robinson, Ashok Veeraraghavan

Diffuse optical tomography (DOT) is one of the most powerful techniques for imaging deep within tissue -- well beyond the conventional $\sim$10-15 mean scattering lengths tolerated by ballistic imaging techniques such as confocal and two-photon microscopy.

Vocal Bursts Intensity Prediction

SACoD: Sensor Algorithm Co-Design Towards Efficient CNN-powered Intelligent PhlatCam

1 code implementation ICCV 2021 Yonggan Fu, Yang Zhang, Yue Wang, Zhihan Lu, Vivek Boominathan, Ashok Veeraraghavan, Yingyan Lin

PhlatCam, with its form factor potentially reduced by orders of magnitude, has emerged as a promising solution to the first aforementioned challenge, while the second one remains a bottleneck.

Benchmarking Model Compression +1

The Benefit of Distraction: Denoising Camera-Based Physiological Measurements Using Inverse Attention

no code implementations ICCV 2021 Ewa M. Nowara, Daniel McDuff, Ashok Veeraraghavan

The core idea is that the signal of interest is stronger in some pixels ("foreground"), and by selectively focusing computation on these pixels, networks can extract subtle information buried in noise and other sources of corruption.


SASSI -- Super-Pixelated Adaptive Spatio-Spectral Imaging

1 code implementation28 Dec 2020 Vishwanath Saragadam, Michael DeZeeuw, Richard Baraniuk, Ashok Veeraraghavan, Aswin Sankaranarayanan

Hence, a scene-adaptive spatial sampling of an hyperspectral scene, guided by its super-pixel segmented image, is capable of obtaining high-quality reconstructions.

How to Train Neural Networks for Flare Removal

1 code implementation ICCV 2021 Yicheng Wu, Qiurui He, Tianfan Xue, Rahul Garg, Jiawen Chen, Ashok Veeraraghavan, Jonathan T. Barron

When a camera is pointed at a strong light source, the resulting photograph may contain lens flare artifacts.

Flare Removal

FlatNet: Towards Photorealistic Scene Reconstruction from Lensless Measurements

1 code implementation29 Oct 2020 Salman S. Khan, Varun Sundar, Vivek Boominathan, Ashok Veeraraghavan, Kaushik Mitra

Lensless imaging has emerged as a potential solution towards realizing ultra-miniature cameras by eschewing the bulky lens in a traditional camera.

The Benefit of Distraction: Denoising Remote Vitals Measurements using Inverse Attention

no code implementations14 Oct 2020 Ewa Nowara, Daniel McDuff, Ashok Veeraraghavan

A convolutional attention network is used to learn which regions of a video contain the physiological signal and generate a preliminary estimate.


Fine-grained Classification using Heterogeneous Web Data and Auxiliary Categories

no code implementations19 Nov 2018 Li Niu, Ashok Veeraraghavan, Ashu Sabharwal

In the extreme case, given a set of test categories without any well-labeled training data, the majority of existing works can be grouped into the following two research directions: 1) crawl noisy labeled web data for the test categories as training data, which is dubbed as webly supervised learning; 2) transfer the knowledge from auxiliary categories with well-labeled training data to the test categories, which corresponds to zero-shot learning setting.

Classification General Classification +3

Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions

1 code implementation ICML 2018 Junru Wu, Yue Wang, Zhen-Yu Wu, Zhangyang Wang, Ashok Veeraraghavan, Yingyan Lin

The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e. g., GoogLeNet, ResNet and Wide ResNet).


Deep $k$-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions

1 code implementation24 Jun 2018 Junru Wu, Yue Wang, Zhen-Yu Wu, Zhangyang Wang, Ashok Veeraraghavan, Yingyan Lin

The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e. g., GoogLeNet, ResNet and Wide ResNet).


Webly Supervised Learning Meets Zero-Shot Learning: A Hybrid Approach for Fine-Grained Classification

no code implementations CVPR 2018 Li Niu, Ashok Veeraraghavan, Ashutosh Sabharwal

The drawbacks of the above two directions motivate us to design a new framework which can jointly leverage both web data and auxiliary labeled categories to predict the test categories that are not associated with any well-labeled training images.

Fine-Grained Image Classification General Classification +2

Fast Retinomorphic Event Stream for Video Recognition and Reinforcement Learning

no code implementations16 May 2018 Wanjia Liu, Huaijin Chen, Rishab Goel, Yuzhong Huang, Ashok Veeraraghavan, Ankit Patel

Good temporal representations are crucial for video understanding, and the state-of-the-art video recognition framework is based on two-stream networks.

Action Recognition Atari Games +8

Learning from Noisy Web Data with Category-level Supervision

no code implementations CVPR 2018 Li Niu, Qingtao Tang, Ashok Veeraraghavan, Ashu Sabharwal

As tons of photos are being uploaded to public websites (e. g., Flickr, Bing, and Google) every day, learning from web data has become an increasingly popular research direction because of freely available web resources, which is also referred to as webly supervised learning.

General Classification

Zero-Shot Learning via Category-Specific Visual-Semantic Mapping

no code implementations16 Nov 2017 Li Niu, Jianfei Cai, Ashok Veeraraghavan

Zero-Shot Learning (ZSL) aims to classify a test instance from an unseen category based on the training instances from seen categories, in which the gap between seen categories and unseen categories is generally bridged via visual-semantic mapping between the low-level visual feature space and the intermediate semantic space.

General Classification Image Classification +2

Online Reweighted Least Squares Algorithm for Sparse Recovery and Application to Short-Wave Infrared Imaging

no code implementations29 Jun 2017 Subhadip Mukherjee, Deepak R., Huaijin Chen, Ashok Veeraraghavan, Chandra Sekhar Seelamantula

The proposed online algorithm is useful in a setting where one seeks to design a progressive decoding strategy to reconstruct a sparse signal from linear measurements so that one does not have to wait until all measurements are acquired.

Spatial Phase-Sweep: Increasing temporal resolution of transient imaging using a light source array

no code implementations21 Dec 2015 Ryuichi Tadano, Adithya Kumar Pediredla, Kaushik Mitra, Ashok Veeraraghavan

Transient imaging or light-in-flight techniques capture the propagation of an ultra-short pulse of light through a scene, which in effect captures the optical impulse response of the scene.

Depth Selective Camera: A Direct, On-Chip, Programmable Technique for Depth Selectivity in Photography

no code implementations ICCV 2015 Ryuichi Tadano, Adithya Kumar Pediredla, Ashok Veeraraghavan

Time of flight (ToF) cameras use a temporally modulated light source and measure correlation between the reflected light and a sensor modulation pattern, in order to infer scene depth.

Toward Long Distance, Sub-diffraction Imaging Using Coherent Camera Arrays

no code implementations28 Oct 2015 Jason Holloway, M. Salman Asif, Manoj Kumar Sharma, Nathan Matsuda, Roarke Horstmeyer, Oliver Cossairt, Ashok Veeraraghavan

Recent advances in ptychography have demonstrated that one can image beyond the diffraction limit of the objective lens in a microscope.

Retrieval Translation

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

no code implementations2 Sep 2015 Suren Jayasuriya, Adithya Pediredla, Sriram Sivaramakrishnan, Alyosha Molnar, Ashok Veeraraghavan

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.

FlatCam: Thin, Bare-Sensor Cameras using Coded Aperture and Computation

2 code implementations1 Sep 2015 M. Salman Asif, Ali Ayremlou, Aswin Sankaranarayanan, Ashok Veeraraghavan, Richard Baraniuk

FlatCam is a thin form-factor lensless camera that consists of a coded mask placed on top of a bare, conventional sensor array.

Image Reconstruction

TabletGaze: Unconstrained Appearance-based Gaze Estimation in Mobile Tablets

no code implementations5 Aug 2015 Qiong Huang, Ashok Veeraraghavan, Ashutosh Sabharwal

We study gaze estimation on tablets, our key design goal is uncalibrated gaze estimation using the front-facing camera during natural use of tablets, where the posture and method of holding the tablet is not constrained.

Gaze Estimation

DistancePPG: Robust non-contact vital signs monitoring using a camera

1 code implementation27 Feb 2015 Mayank Kumar, Ashok Veeraraghavan, Ashutosh Sabharval

The gains in SNR of camera-based PPG estimated using distancePPG translate into reduction of the error in vital sign estimation, and thus expand the scope of camera-based vital sign monitoring to potentially challenging scenarios.

Fast Sublinear Sparse Representation using Shallow Tree Matching Pursuit

no code implementations1 Dec 2014 Ali Ayremlou, Thomas Goldstein, Ashok Veeraraghavan, Richard Baraniuk

Sparse approximations using highly over-complete dictionaries is a state-of-the-art tool for many imaging applications including denoising, super-resolution, compressive sensing, light-field analysis, and object recognition.

Compressive Sensing Image Denoising +2

A Framework for the Analysis of Computational Imaging Systems with Practical Applications

no code implementations8 Aug 2013 Kaushik Mitra, Oliver Cossairt, Ashok Veeraraghavan

Unfortunately, a detailed analysis of CI has proven to be a challenging problem because performance depends equally on three components: (1) the optical multiplexing, (2) the noise characteristics of the sensor, and (3) the reconstruction algorithm.


Cannot find the paper you are looking for? You can Submit a new open access paper.