Department of Computer Science & Engineering

&ldquo;IIT Jodhpur is committed to impart quality education to facilitate the creation of qualified, competent and responsible human resources to meet the emerging technological challenges of the world. It is working towards creating an equitable learning platform that is positive, accessible and effective in the face of the modern societal and scientific advancements.

Flexibility in curriculum, in all its academic programs, encompassing elements of teaching, research, creativity, innovation and entrepreneurship is the most unique feature of IIT Jodhpur. The Department of Science and Technology (DST), under the National Mission on Cyber Physical Systems, has identified IIT Jodhpur as a Technology &amp; Innovation Hub in the area of Augmented Reality and Virtual Reality. The institute has also been nominated as the coordinator for the Jodhpur City and Knowledge Cluster by the Office of Principal Scientific Adviser, Government of India.

The sprawling 852-acre IIT Jodhpur campus is a majestic tribute to the deep-rooted diverse cultural heritage of the region. The campus is an architectural masterpiece, which is slated to become an international exemplar of sustainability with net-zero energy, and advanced water and waste management strategies.&rdquo;

IIT Jodhpur

In this paper, we develop a robust 3D garment digitization solution that can generalize well on real-world fashion catalog images with cloth texture occlusions and large body pose variations. We assumed fixed topology parametric template mesh models for known types of garments (e.g., T-shirts, Trousers) and perform mapping of high-quality texture from an input catalog image to UV map panels corresponding to the parametric mesh model of the garment. We achieve this by first predicting a sparse set of 2D landmarks on the boundary of the garments. Subsequently, we use these landmarks to perform Thin-Plate-Spline-based texture transfer on UV map panels. Subsequently, we employ a deep texture inpainting network to fill the large holes (due to view variations self-occlusions) in TPS output to generate consistent UV maps. Furthermore, to train the supervised deep networks for landmark prediction texture inpainting tasks, we generated a large set of synthetic data with varying texture and lighting imaged from various views with the human present in a wide variety of poses. Additionally, we manually annotated a small set of fashion catalog images crawled from online fashion e-commerce platforms to finetune. We conduct thorough empirical evaluations and show impressive qualitative results of our proposed 3D garment texture solution on fashion catalog images. Such 3D garment digitization helps us solve the challenging task of enabling 3D Virtual Try-on. © 2022 IEEE.

World University root node

Proceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022

Robust 3D Garment Digitization from Monocular 2D Images for 3D Virtual Try-On Systems

Reconfiguring two shortest paths in a graph means modifying one shortest path to the other by changing one vertex at a time, so that all the intermediate paths are also shortest paths. This problem has several natural applications, namely: (a) revamping road networks, (b) rerouting data packets in a synchronous multiprocessing setting, (c) the shipping container stowage problem, and (d) the train marshalling problem. When modelled as graph problems, (a) is the most general case while (b), (c) and (d) are restrictions to different graph classes. We show that (a) is intractable, even for relaxed variants of the problem. For (b), (c) and (d), we present efficient algorithms to solve the respective problems. We also generalize the problem to when at most k (for some k ≥ 2) contiguous vertices on a shortest path can be changed at a time. Copyright © 2022, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022

Reconfiguring Shortest Paths in Graphs

Over the last decade, there has been growing interest in learning the mapping from structural connectivity (SC) to functional connectivity (FC) of the brain. The spontaneous brain activity fluctuations during the resting-state as captured by functional MRI (rsfMRI) contain rich non-stationary dynamics over a relatively fixed structural connectome. Among the modeling approaches, graph diffusion-based methods with single and multiple diffusion kernels approximating static or dynamic functional connectivity have shown promise in predicting the FC given the SC. However, these methods are computationally expensive, not scalable, and fail to capture the complex dynamics underlying the whole process. Recently, deep learning methods such as GraphHeat networks along with graph diffusion have been shown to handle complex relational structures while preserving global information. In this paper, we propose multiple GraphHeat networks (M-GHN), a novel approach for mapping SC-FC. M-GHN enables us to model multiple heat kernel diffusion over the brain graph for approximating the complex Reaction Diffusion phenomenon. We argue that the proposed deep learning method overcomes the scalability and computational inefficiency issues but can still learn the SC-FC mapping successfully. Training and testing were done using the rsfMRI data of 100 participants from the human connectome project (HCP), and the results establish the viability of the proposed model. On the HCP dataset of 100 participants, the M-GHN achieves a high Pearson correlation of 0.747. Furthermore, experiments demonstrate that M-GHN outperforms the existing methods in learning the complex nature of human brain function. © 2022 IEEE.

Proceedings of the International Joint Conference on Neural Networks

Multiple GraphHeat Networks for Structural to Functional Brain Mapping

This paper proposes a novel adaptive multi-resolution framework for generating terrains. Our framework combines diffusion-based generative network and novel frequency separated terrain features for terrain patch generation. Additionally, we propose to leverage learnable terrain super-resolution for enhancing generated terrain patch followed by novel kernel-based blending of these patches using Perlin noise to generate infinite terrain with realistic terrain features. We provide a comprehensive quantitative and qualitative evaluation of the proposed framework. © 2022 ACM.

ACM International Conference Proceeding Series

Adaptive &amp; Multi-Resolution Procedural Infinite Terrain Generation with Diffusion Models and Perlin Noise

Knowledge-Based Systems

Dual class representation learning for few-shot image classification

Neurocomputing

Few-shot image classification with composite rotation based self-supervised auxiliary task

Human mind processes the different primitive components of image signals such as color, shape, texture, and symmetry in a parallel and complex fashion. Deep neural networks aim to learn all these components from the image in an unsupervised manner. However, learning the primitive features is not formally assured in a deep learning formulation, and, adding these features explicitly would improve the performance. Especially in face recognition, humans intuitively and implicitly employ the usage of primitive features such as color, shape, texture, and symmetry of faces. Inspired by this observation, this paper presents a novel approach in building a learning based TeCS2 space. This space consists of meta-level features obtained from dictionary learning and combining it with task specific deep learning classifiers (such as DenseNet) for face recognition. Confidence based fusion mechanism is presented to supplement the task specific deep learning classifier with the proposed TeCS2 features. The effectiveness of the proposed framework is evaluated on four benchmark face recognition datasets: (i) Disguised Faces in the Wild (DFW), (ii) Labeled faces in the wild (LFW), (iii) IIITD Plastic Surgery dataset, and (iv) Point and Shoot Challenge (PaSC). © 2021

Pattern Recognition Letters

Improving face recognition performance using TeCS2 dictionary

One of the most crucial and informative tools available at the disposal of a Cardiologist for examining the condition of a patient’s cardiovascular system is the electrocardiogram (ECG/EKG). A major reason behind the need for accurate reconstruction of ECG comes from the fact that the shape of ECG tracing is very crucial for determining the health condition of an individual. Whether the patient is prone to or diagnosed with cardiovascular diseases (CVDs), this information can be gathered through examination of ECG signal. Among various other methods, one of the most helpful methods in identifying cardiac abnormalities is a beat-wise categorization of a patient’s ECG record. In this work, a highly efficient deep representation learning approach for ECG beat classification is proposed, which can significantly reduce the burden and time spent by a Cardiologist for ECG Analysis. This work consists of two sub-systems: denoising block and beat classification block. The initial block is a denoising block that acquires the ECG signal from the patient and denoises that. The next stage is the beat classification part. This processes the input ECG signal for finding out the different classes of beats in the ECG through an efficient algorithm. In both stages, deep learning-based methods have been employed for the purpose. Our proposed approach has been tested on PhysioNet’s MIT-BIH Arrhythmia Database, for beat-wise classification into ten important types of heartbeats. As per the results obtained, the proposed approach is capable of making meaningful predictions and gives superior results on relevant metrics. © 2021, Korean Society of Medical and Biological Engineering.

Biomedical Engineering Letters

HeartNetEC: a deep representation learning approach for ECG beat classification

In the forthcoming 5G technology, Sparse Code Multiple Access (SCMA) is the most promising scheme that aims at improving spectral efficiency further and providing massive connectivity. The challenge behind implementing SCMA scheme is: constructing optimized codebooks in order to obtain minimum BER while keeping the receiver complexity minimum. To address this problem, we resort to the usage of an efficient deep learning technique, autoencoders, that club the encoder and the decoder part and automatically learn the most optimum codeword that could give the least BER. In this paper, SCMA sparse autoencoder, which is a variant of the autoencoder, is proposed, that has better BER performance than a conventional autoencoder, without paying in terms of computational complexity. © 2021 IEEE.

3rd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2021

Sparse Autoencoder for Sparse Code Multiple Access

In the field of digital communication, there has always been a requirement for an efficient, low complex, and high-speed error control encoder and decoder. Many such encoders and decoders for different error control codes have been proposed in the literature by researchers. However, developing such CODECs whose performance can be suitable for the requirements of modern communication systems is still an open research problem. In this paper, one such decoder, namely fast Chase decoder proposed in the literature, has been studied. The hardware design of the decoder has been done and verified with results from MATLAB simulations. An attempt has been made to improve the speed by replacing the ripple carry adder in the design with a fast adder. The hardware architecture is implemented in Xilinx XC7A35T platform, and an increase in computation speed of 5% has been achieved. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.