Search Results for author:
Found 49 papers, 7 papers with code
Learning Robust Deep Visual Representations from EEG Brain Recordings
Reconstruction of visual images from brain Electroencephalography (EEG) signals has garnered a lot of interest due to its applications in brain-computer interfacing.
Single Image LDR to HDR Conversion using Conditional Diffusion
Digital imaging aims to replicate realistic scenes, but Low Dynamic Range (LDR) cameras cannot represent the wide dynamic range of real scenes, resulting in under-/overexposed images.
A Graph Neural Network Approach for Temporal Mesh Blending and Correspondence
We have proposed a self-supervised deep learning framework for solving the mesh blending problem in scenarios where the meshes are not in correspondence.
PointResNet: Residual Network for 3D Point Cloud Segmentation and Classification
Point cloud segmentation and classification are some of the primary tasks in 3D computer vision with applications ranging from augmented reality to robotics.
Revisiting Heterophily in Graph Convolution Networks by Learning Representations Across Topological and Feature Spaces
Graph convolution networks (GCNs) have been enormously successful in learning representations over several graph-based machine learning tasks.
DeepHS-HDRVideo: Deep High Speed High Dynamic Range Video Reconstruction
Previous works in high dynamic range (HDR) video reconstruction uses sequence of alternating exposure LDR frames as input, and align the neighbouring frames using optical flow based networks.
DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images
Despite the success of existing traditional and deep learning-based methods, it is still challenging due to: (i) the requirement of three or more differently illuminated images, (ii) the inability to model unknown general reflectance, and (iii) the requirement of accurate 3D ground truth surface normals and known lighting information for training.
FMD-cGAN: Fast Motion Deblurring using Conditional Generative Adversarial Networks
With the help of MobileNet based architecture that consists of depthwise separable convolution, we reduce the model size and inference time, without losing the quality of the images.
HDRVideo-GAN: Deep Generative HDR Video Reconstruction
We first extract clean LDR frames from noisy LDR video with alternating exposures with a denoising network trained in a self-supervised setting.
TreeGCN-ED: Encoding Point Cloud using a Tree-Structured Graph Network
Point cloud is one of the widely used techniques for representing and storing 3D geometric data.
HDR-cGAN: Single LDR to HDR Image Translation using Conditional GAN
Specifically, saturation in overexposed regions makes the task of reconstructing a High Dynamic Range (HDR) image from single LDR image challenging.
Shadow Art Revisited: A Differentiable Rendering Based Approach
In this work, we revisit shadow art using differentiable rendering based optimization frameworks to obtain the 3D sculpture from a set of shadow (binary) images and their corresponding projection information.
RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assembly
Autonomous assembly of objects is an essential task in robotics and 3D computer vision.
ShuffleBlock: Shuffle to Regularize Deep Convolutional Neural Networks
This paper studies the operation of channel shuffle as a regularization technique in deep convolutional networks.
LS-HDIB: A Large Scale Handwritten Document Image Binarization Dataset
This work proposes LS-HDIB - a large-scale handwritten document image binarization dataset containing over a million document images that span numerous real-world scenarios.
APEX-Net: Automatic Plot Extractor Network
To minimize this intervention, we propose APEX-Net, a deep learning based framework with novel loss functions for solving the plot extraction problem.
DILIE: Deep Internal Learning for Image Enhancement
Recent methods for image enhancement consider the problem by performing style transfer and image restoration.
DeepObjStyle: Deep Object-based Photo Style Transfer
DeepObjStyle preserves the semantics of the objects and achieves better style transfer in the challenging scenario when the style and the content images have a mismatch of image features.
Blind Motion Deblurring through SinGAN Architecture
SinGAN is a generative model that is unconditional and could be learned from a single natural image.
DeepCFL: Deep Contextual Features Learning from a Single Image
In this work, we proposed a new training data-independent framework, called Deep Contextual Features Learning (DeepCFL), to perform image synthesis and image restoration based on the semantics of the input image.
Learning to Sort Image Sequences via Accumulated Temporal Differences
Let the temporal order in which these images are captured be unknown.
Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition
To address these issues, we propose spatio-temporal short term Fourier transform (STFT) blocks, a new class of convolutional blocks that can serve as an alternative to the 3D convolutional layer and its variants in 3D CNNs.
Yoga-82: A New Dataset for Fine-grained Classification of Human Poses
To handle more variety in human poses, we propose the concept of fine-grained hierarchical pose classification, in which we formulate the pose estimation as a classification task, and propose a dataset, Yoga-82, for large-scale yoga pose recognition with 82 classes.
Deep No-reference Tone Mapped Image Quality Assessment
The novelty of this work is its ability to visualize various distortions as quality maps (distortion maps), especially in the no-reference setting, and to use these maps as features to estimate the quality score of tone mapped images.
Depthwise-STFT based separable Convolutional Neural Networks
In this paper, we propose a new convolutional layer called Depthwise-STFT Separable layer that can serve as an alternative to the standard depthwise separable convolutional layer.
FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network
High dynamic range (HDR) image generation from a single exposure low dynamic range (LDR) image has been made possible due to the recent advances in Deep Learning.
Simultaneous Detection and Removal of Dynamic Objects in Multi-view Images
During the scan, when a pixel is classified as dynamic, the proposed algorithm replaces that pixel value with the corresponding pixel value of the static region which is being occluded by that dynamic region.
DCIL: Deep Contextual Internal Learning for Image Restoration and Image Retargeting
Recently, there is a vast interest in developing methods which are independent of the training samples such as deep image prior, zero-shot learning, and internal learning.
DeepPFCN: Deep Parallel Feature Consensus Network For Person Re-Identification
This model factorizes the visual appearance of a person into latent discriminative factors at multiple semantic levels.
Exploring Temporal Differences in 3D Convolutional Neural Networks
Traditional 3D convolutions are computationally expensive, memory intensive, and due to large number of parameters, they often tend to overfit.
Multi-level Encoder-Decoder Architectures for Image Restoration
In this paper, we propose a framework based on the multi-level extensions of the encoder-decoder network, to investigate interesting aspects of the relationship between image restoration and network construction independent of learning.
Attentive Spatio-Temporal Representation Learning for Diving Classification
The proposed model outperforms the classification accuracy of the state-of-the-art models in both 2D and 3D frameworks by 11. 54% and 4. 24%, respectively.
LBVCNN: Local Binary Volume Convolutional Neural Network for Facial Expression Recognition from Image Sequences
Recognizing facial expressions is one of the central problems in computer vision.
Facial Expression Recognition
Facial Expression Recognition (FER)
LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks
The ReLPV block extracts the phase in a 3D local neighborhood (e. g., 3x3x3) of each position of the input map to obtain the feature maps.
Fast and Accurate Intrinsic Symmetry Detection
In this work, we detect the intrinsic reflective symmetry in triangle meshes where we have to find the intrinsically symmetric point for each point of the shape.
SymmSLIC: Symmetry Aware Superpixel Segmentation and its Applications
We partition the image into superpixels while preserving this reflection symmetry through an iterative algorithm.
Deep Generative Filter for Motion Deblurring
Removing blur caused by camera shake in images has always been a challenging problem in computer vision literature due to its ill-posed nature.
Facial Expression Recognition using Visual Saliency and Deep Learning
We have developed a convolutional neural network for the purpose of recognizing facial expressions in human beings.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
Automatic Trimap Generation for Image Matting
We use learning based matting method to generate the matte from the automatically generated trimap.
Iterative Spectral Clustering for Unsupervised Object Localization
This paper addresses the problem of unsupervised object localization in an image.
Flow-free Video Object Segmentation
Our algorithm segments various object instances appearing in the video and then perform clustering in order to group visually similar segments into one cluster.
Detecting Approximate Reflection Symmetry in a Point Set using Optimization on Manifold
We formulate an optimization framework in which the problem of establishing the correspondences amounts to solving a linear assignment problem and the problem of determining the reflection symmetry transformation amounts to solving an optimization problem on a smooth Riemannian product manifold.
Hashing in the Zero Shot Framework with Domain Adaptation
Therefore, we propose an algorithm to learn a hash function from training images belonging to `seen' classes which can efficiently encode images of `unseen' classes to binary codes.
Zero Shot Hashing
In this work, we attempt to generate the hash codes for images belonging to unseen classes, information of which is available only through the textual corpus.
Automatic Segmentation of Dynamic Objects from an Image Pair
Automatic segmentation of objects from a single image is a challenging problem which generally requires training on large number of images.
Automatic Content-aware Non-Photorealistic Rendering of Images
Non-photorealistic rendering techniques work on image features and often manipulate a set of characteristics such as edges and texture to achieve a desired depiction of the scene.
Effective Object Tracking in Unstructured Crowd Scenes
The analysis shows the advantages and limitations of the proposed approach for tracking an object in unstructured crowd scenes.
SA-CNN: Dynamic Scene Classification using Convolutional Neural Networks
The task of classifying videos of natural dynamic scenes into appropriate classes has gained lot of attention in recent years.
Efficient Image Retargeting for High Dynamic Range Scenes
In this paper, we address the problem of displaying the high contrast low dynamic range (LDR) image of a HDR scene in a display device which has different spatial resolution compared to that of the capturing digital camera.
