Search Results for author:
Found 46 papers, 8 papers with code
PNeRV: A Polynomial Neural Representation for Videos
Extracting Implicit Neural Representations (INRs) on video data poses unique challenges due to the additional temporal dimension.
Spatially-Attentive Patch-Hierarchical Network with Adaptive Sampling for Motion Deblurring
This paper tackles the problem of motion deblurring of dynamic scenes.
Latents2Semantics: Leveraging the Latent Space of Generative Models for Localized Style Manipulation of Face Images
Consequentially, style editing of the chosen ROIs amounts to a simple combination of (a) the ROI-mask generated from the sliced structure representation and (b) the decoded image with global style changes, generated from the manipulated (using Gaussian noise) global style and unchanged structure tensor.
Unsupervised network for low-light enhancement
Different ablation studies show the importance of PAM and CIN in improving the visible quality of the image.
Zero shot framework for satellite image restoration
We then propose the use of knowledge distillation to train a restoration network using the generated image pairs.
Unsupervised haze removal from underwater images
Several supervised networks exist that remove haze information from underwater images using paired datasets and pixel-wise loss functions.
Improving Robustness of Semantic Segmentation to Motion-Blur Using Class-Centric Augmentation
Semantic segmentation involves classifying each pixel into one of a pre-defined set of object/stuff classes.
Self-supervised Monocular Underwater Depth Recovery, Image Restoration, and a Real-sea Video Dataset
To obtain improved estimates of depth from a single UW image, we propose a deep learning (DL) method that utilizes both haze and geometry during training.
Exploring the Effectiveness of Mask-Guided Feature Modulation as a Mechanism for Localized Style Editing of Real Images
Both inversion of real images and determination of controllable latent directions are computationally expensive operations.
Hybrid Transformer Based Feature Fusion for Self-Supervised Monocular Depth Estimation
Our model fuses per-pixel local information learned using two fully convolutional depth encoders with global contextual information learned by a transformer encoder at different scales.
Latents2Segments: Disentangling the Latent Space of Generative Models for Semantic Segmentation of Face Images
Our endeavour in this work is to do away with the priors and complex pre-processing operations required by SOTA multi-class face segmentation models by reframing this operation as a downstream task post infusion of disentanglement with respect to facial semantic regions of interest (ROIs) in the latent space of a Generative Autoencoder model.
Deep Networks for Image and Video Super-Resolution
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 Superresolution using Scale-Recurrent Dense Network
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.
Unfolding a blurred image
This network extracts embedded motion information from the blurred image to generate a sharp video in conjunction with the trained recurrent video decoder.
Image Restoration using Feature-guidance
Image restoration is the task of recovering a clean image from a degraded version.
Adaptive Image Inpainting
We deploy cross and self distillation techniques and discuss the need for a dedicated completion-block in encoder to achieve the distillation target.
Dynamic Scene Video Deblurring using Non-Local Attention
This paper tackles the challenging problem of video deblurring.
Mitigating Channel-wise Noise for Single Image Super Resolution
In practice, images can contain different amounts of noise for different color channels, which is not acknowledged by existing super-resolution approaches.
Deep network for rolling shutter rectification
The motion block predicts camera pose for every row of the input RS distorted image while the trajectory module fits estimated motion parameters to a third-order polynomial.
IR Motion Deblurring
Such datasets which are a rarity can be a valuable asset for contemporary deep learning methods.
Spatially-Adaptive Image Restoration using Distortion-Guided Networks
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.
Gated Spatio-Temporal Attention-Guided Video Deblurring
Video deblurring remains a challenging task due to the complexity of spatially and temporally varying blur.
Distillation-Guided Image Inpainting
Image inpainting methods have shown significant improvements by using deep neural networks recently.
Localize to Binauralize: Audio Spatialization From Visual Sound Source Localization
Through user study, we further validate that our proposed approach generates binaural-quality audio using as little as 10% of explicit binaural supervision data for the SG network.
AIM 2020 Challenge on Rendering Realistic Bokeh
This paper reviews the second AIM realistic bokeh effect rendering challenge and provides the description of the proposed solutions and results.
AIM 2020: Scene Relighting and Illumination Estimation Challenge
The first track considered one-to-one relighting; the objective was to relight an input photo of a scene with a different color temperature and illuminant orientation (i. e., light source position).
Unpaired Image Denoising
A majority of methods for image denoising are no exception to this rule and hence demand pairs of noisy and corresponding clean images.
Image and Video Processing
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.
Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring
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 #33 on
Image Deblurring
on GoPro
(using extra training data)
Region-Adaptive Dense Network for Efficient Motion Deblurring
In this paper, we address the problem of dynamic scene deblurring in the presence of motion blur.
AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results
For training, only one set of source input images is therefore provided in the challenge.
AIM 2019 Challenge on Image Demoireing: Methods and Results
A new dataset, called LCDMoire was created for this challenge, and consists of 10, 200 synthetically generated image pairs (moire and clean ground truth).
Planar Geometry and Image Recovery from Motion-Blur
We first propose an approach for estimation of normal of a planar scene from a single motion blurred observation.
Motion Deblurring with an Adaptive Network
In this paper, we address the problem of dynamic scene deblurring in the presence of motion blur.
Ranked #32 on
Image Deblurring
on GoPro
(using extra training data)
PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones.
Unsupervised Class-Specific Deblurring
To improve the stability of GAN and to preserve the image correspondence, we introduce an additional CNN module that reblurs the generated GAN output to match with the blurred input.
Occlusion-Aware Rolling Shutter Rectification of 3D Scenes
Due to the sequential mechanism, images acquired with a moving camera are subjected to rolling shutter effect which manifests as geometric distortions.
Non-Blind Deblurring: Handling Kernel Uncertainty With CNNs
Blind motion deblurring methods are primarily responsible for recovering an accurate estimate of the blur kernel.
Divide and Conquer for Full-Resolution Light Field Deblurring
Consequently, blind deblurring of any single subaperture image elegantly paves the way for cost-effective non-blind deblurring of the other subaperture images.
Bringing Alive Blurred Moments
This network extracts embedded motion information from the blurred image to generate a sharp video in conjunction with the trained recurrent video decoder.
Ranked #43 on
Image Deblurring
on GoPro
(using extra training data)
Going Unconstrained With Rolling Shutter Deblurring
Most present-day imaging devices are equipped with CMOS sensors.
Blur-Invariant Deep Learning for Blind-Deblurring
In this paper, we investigate deep neural networks for blind motion deblurring.
From Local to Global: Edge Profiles to Camera Motion in Blurred Images
In this work, we investigate the relation between the edge profiles present in a motion blurred image and the underlying camera motion responsible for causing the motion blur.
Unrolling the Shutter: CNN to Correct Motion Distortions
Our single-image correction method fares well even operating in a frame-by-frame manner against video-based methods and performs better than scene-specific correction schemes even under challenging situations.
Rolling Shutter Super-Resolution
But CMOS sensors that have increasingly started to replace their more expensive CCD counterparts in many applications do not respect this assumption if there is a motion of the camera relative to the scene during the exposure duration of an image because of the row-wise acquisition mechanism.
