Search Results for author: Kuldeep Purohit

Found 19 papers, 5 papers with code

Unfolding a blurred image

no code implementations28 Jan 2022 Kuldeep Purohit, Anshul Shah, A. N. Rajagopalan

This network extracts embedded motion information from the blurred image to generate a sharp video in conjunction with the trained recurrent video decoder.

Deblurring Image Deblurring +1

Deep Networks for Image and Video Super-Resolution

no code implementations28 Jan 2022 Kuldeep Purohit, Srimanta Mandal, A. N. Rajagopalan

To enable super-resolution for multiple factors, we propose a scale-recurrent framework which reutilizes the filters learnt for lower scale factors recursively for higher factors.

Image Super-Resolution Single Image Super Resolution +1

Image Superresolution using Scale-Recurrent Dense Network

no code implementations28 Jan 2022 Kuldeep Purohit, Srimanta Mandal, A. N. Rajagopalan

In this paper, we propose a scale recurrent SR architecture built upon units containing series of dense connections within a residual block (Residual Dense Blocks (RDBs)) that allow extraction of abundant local features from the image.

Image Super-Resolution

Adaptive Image Inpainting

no code implementations1 Jan 2022 Maitreya Suin, Kuldeep Purohit, A. N. Rajagopalan

We deploy cross and self distillation techniques and discuss the need for a dedicated completion-block in encoder to achieve the distillation target.

Image Inpainting

Mitigating Channel-wise Noise for Single Image Super Resolution

no code implementations14 Dec 2021 Srimanta Mandal, Kuldeep Purohit, A. N. Rajagopalan

In practice, images can contain different amounts of noise for different color channels, which is not acknowledged by existing super-resolution approaches.

Image Super-Resolution Single Image Super Resolution

Spatially-Adaptive Image Restoration using Distortion-Guided Networks

no code implementations ICCV 2021 Kuldeep Purohit, Maitreya Suin, A. N. Rajagopalan, Vishnu Naresh Boddeti

However, we hypothesize that such spatially rigid processing is suboptimal for simultaneously restoring the degraded pixels as well as reconstructing the clean regions of the image.

Image Restoration

Distillation-Guided Image Inpainting

no code implementations ICCV 2021 Maitreya Suin, Kuldeep Purohit, A. N. Rajagopalan

Image inpainting methods have shown significant improvements by using deep neural networks recently.

Image Inpainting

Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring

no code implementations CVPR 2020 Maitreya Suin, Kuldeep Purohit, A. N. Rajagopalan

Existing approaches achieve a large receptive field by increasing the number of generic convolution layers and kernel-size, but this comes at the expense of of the increase in model size and inference speed.

Ranked #14 on Image Deblurring on GoPro (using extra training data)

Deblurring Image Deblurring

Planar Geometry and Image Recovery from Motion-Blur

no code implementations7 Apr 2019 Kuldeep Purohit, Subeesh Vasu, M. Purnachandra Rao, A. N. Rajagopalan

We first propose an approach for estimation of normal of a planar scene from a single motion blurred observation.

Deblurring

Motion Deblurring with an Adaptive Network

no code implementations25 Mar 2019 Kuldeep Purohit, A. N. Rajagopalan

In this paper, we address the problem of dynamic scene deblurring in the presence of motion blur.

Ranked #13 on Image Deblurring on GoPro (using extra training data)

Deblurring Image Deblurring

Bringing Alive Blurred Moments

1 code implementation CVPR 2019 Kuldeep Purohit, Anshul Shah, A. N. Rajagopalan

This network extracts embedded motion information from the blurred image to generate a sharp video in conjunction with the trained recurrent video decoder.

Ranked #22 on Image Deblurring on GoPro (using extra training data)

Deblurring Image Deblurring +1

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