Search Results for author: Kaushik Mitra

Found 28 papers, 12 papers with code

Restoring Extremely Dark Images in Real Time

1 code implementation CVPR 2021 Mohit Lamba, Kaushik Mitra

We propose a new deep learning architecture for extreme low-light single image restoration, which is exceptionally lightweight, remarkably fast, and produces a restoration that is perceptually at par with state-of-the-art computationally intense models.

Image Restoration Low-Light Image Enhancement +1

V-DESIRR: Very Fast Deep Embedded Single Image Reflection Removal

1 code implementation ICCV 2021 B H Pawan Prasad, Green Rosh K S, Lokesh R. Boregowda, Kaushik Mitra, Sanjoy Chowdhury

Our method processes the corrupted image in two stages, a Low Scale Sub-network (LSSNet) to process the lowest scale and a Progressive Inference (PI) stage to process all the higher scales.

Reflection Removal

Towards Fast and Light-Weight Restoration of Dark Images

1 code implementation28 Nov 2020 Mohit Lamba, Atul Balaji, Kaushik Mitra

However, doing the bulk of computations in the LR space causes artifacts in the restored image.

Image Reconstruction

A Unified Framework for Compressive Video Recovery from Coded Exposure Techniques

1 code implementation11 Nov 2020 Prasan Shedligeri, Anupama S, Kaushik Mitra

Most recently, a Coded-2-Bucket camera has been proposed that can acquire two compressed measurements in a single exposure, unlike previously proposed coded exposure techniques, which can acquire only a single measurement.

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.

Deep Atrous Guided Filter for Image Restoration in Under Display Cameras

1 code implementation14 Aug 2020 Varun Sundar, Sumanth Hegde, Divya Kothandaraman, Kaushik Mitra

In this work, we present Deep Atrous Guided Filter (DAGF), a two-stage, end-to-end approach for image restoration in UDC systems.

Image Restoration

Monocular Retinal Depth Estimation and Joint Optic Disc and Cup Segmentation using Adversarial Networks

no code implementations15 Jul 2020 Sharath M. Shankaranarayana, Keerthi Ram, Kaushik Mitra, Mohanasankar Sivaprakasam

One of the important parameters for the assessment of glaucoma is optic nerve head (ONH) evaluation, which usually involves depth estimation and subsequent optic disc and cup boundary extraction.

Depth Estimation

Pyramidal Edge-maps and Attention based Guided Thermal Super-resolution

no code implementations13 Mar 2020 Honey Gupta, Kaushik Mitra

Guided super-resolution (GSR) of thermal images using visible range images is challenging because of the difference in the spectral-range between the images.

Super-Resolution

Optimal HDR and Depth from Dual Cameras

no code implementations12 Mar 2020 Pradyumna Chari, Anil Kumar Vadathya, Kaushik Mitra

Finally, we present for the first time a stereo HDR dataset consisting of dense ISO and exposure stack captured from a smartphone dual camera.

Disparity Estimation

Harnessing Multi-View Perspective of Light Fields for Low-Light Imaging

1 code implementation5 Mar 2020 Mohit Lamba, Kranthi Kumar, Kaushik Mitra

The proposed L3Fnet not only performs the necessary visual enhancement of each LF view but also preserves the epipolar geometry across views.

Depth Estimation

multi-patch aggregation models for resampling detection

1 code implementation3 Mar 2020 Mohit Lamba, Kaushik Mitra

Images captured nowadays are of varying dimensions with smartphones and DSLR's allowing users to choose from a list of available image resolutions.

Image Manipulation

Unsupervised Single Image Underwater Depth Estimation

1 code implementation25 May 2019 Honey Gupta, Kaushik Mitra

We evaluate and compare our method both quantitatively and qualitatively on various underwater images with diverse attenuation and scattering conditions and show that our method produces state-of-the-art results for unsupervised depth estimation from a single underwater image.

Depth Estimation

Fully Convolutional Networks for Monocular Retinal Depth Estimation and Optic Disc-Cup Segmentation

no code implementations4 Feb 2019 Sharath M. Shankaranarayana, Keerthi Ram, Kaushik Mitra, Mohanasankar Sivaprakasam

Glaucoma is a serious ocular disorder for which the screening and diagnosis are carried out by the examination of the optic nerve head (ONH).

Depth Estimation

A Unified Learning Based Framework for Light Field Reconstruction from Coded Projections

no code implementations26 Dec 2018 Anil Kumar Vadathya, Sharath Girish, Kaushik Mitra

Here, we present a unified learning framework that can reconstruct LF from a variety of multiplexing schemes with minimal number of coded images as input.

Photorealistic Image Reconstruction from Hybrid Intensity and Event based Sensor

no code implementations16 May 2018 Prasan A Shedligeri, Kaushik Mitra

Event sensors output a stream of asynchronous brightness changes (called ``events'') at a very high temporal rate.

Image Reconstruction

Phase retrieval for Fourier Ptychography under varying amount of measurements

no code implementations9 May 2018 Lokesh Boominathan, Mayug Maniparambil, Honey Gupta, Rahul Baburajan, Kaushik Mitra

For the low overlap case we show that a supervised deep learning technique using an autoencoder generator is a good choice for solving the Fourier ptychography problem.

Dynamic Vision Sensors for Human Activity Recognition

1 code implementation13 Mar 2018 Stefanie Anna Baby, Bimal Vinod, Chaitanya Chinni, Kaushik Mitra

We propose to use the various slices (such as $x-y$, $x-t$, and $y-t$) of the DVS video as a feature map for HAR and denote them as Motion Maps.

Activity Recognition

Solving Inverse Computational Imaging Problems using Deep Pixel-level Prior

1 code implementation27 Feb 2018 Akshat Dave, Anil Kumar Vadathya, Ramana Subramanyam, Rahul Baburajan, Kaushik Mitra

On the other hand, a more flexible approach would be to learn a deep generative model once and then use it as a signal prior for solving various inverse problems.

Learning Light Field Reconstruction from a Single Coded Image

no code implementations20 Jan 2018 Anil Kumar Vadathya, Saikiran Cholleti, Gautham Ramajayam, Vijayalakshmi Kanchana, Kaushik Mitra

We propose to do this in three stages 1) reconstruction of center view from the coded image 2) estimating disparity map from the coded image and center view 3) warping center view using the disparity to generate light field.

Dictionary Learning Disparity Estimation

Data Driven Coded Aperture Design for Depth Recovery

no code implementations29 May 2017 Prasan A Shedligeri, Sreyas Mohan, Kaushik Mitra

To address this drawback we propose a data driven approach for learning the optimal aperture pattern to recover depth map from a single coded image.

Compressive Image Recovery Using Recurrent Generative Model

no code implementations13 Dec 2016 Akshat Dave, Anil Kumar Vadathya, Kaushik Mitra

Reconstruction of signals from compressively sensed measurements is an ill-posed problem.

Image Reconstruction

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.

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.

Deblurring

Large-Scale Matrix Factorization with Missing Data under Additional Constraints

no code implementations NeurIPS 2010 Kaushik Mitra, Sameer Sheorey, Rama Chellappa

We further demonstrate the effectiveness of the proposed algorithm in solving the affine SfM problem, non-rigid SfM and photometric stereo problems.

Matrix Completion

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