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

An active area of research in cognitive science is characterizing the relationship between brain structure and the observed functional activations. Recent graph diffusion models have had great success in mapping whole-brain, resting-state dynamics measured using functional Magnetic Resonance Imaging (fMRI) to the brain structure derived using diffusion and T1 brain imaging. Here we test the application of one such graph diffusion method called the Multiple Kernel Learning (MKL) model. MKL model, formulated as a reaction-diffusion system using Wilson-Cowan equations, combines multiple diffusion kernels at different scales to predict functional connectome (FC) arising from a fixed structural connectome (SC). Our simulation results demonstrate that the MKL model successfully mapped the relationship between SC and FC from five different Electroen-cephalogram (EEG) bands (delta, theta, alpha, beta, and gamma). We used simultaneously acquired EEG-fMRI and NODDI dataset of 17 participants. The correlation between predicted FC and ground truth FC was higher for EEG bands than for fMRI data. The prediction accuracy peaked for the alpha band, and the highest frequency band, gamma had the lowest prediction accuracy. To the best of our knowledge, this is the first such end-to-end application of multiple kernel graph diffusion framework for modeling EEG data. One of the important features of MKL model is its ability to incorporate structural connectivity features into the generative model that predicts the EEG functional connectivity. © 2022 IEEE.

World University root node

Proceedings of the International Joint Conference on Neural Networks

Multiple Kernel Learning for Modeling Resting State EEG Connectomes using Structural Connectivity of the Brain

Automated generation and (user) authoring of realistic virtual terrain is most sought for by the multimedia applications like VR models and gaming. The most common representation adopted for terrain is Digital Elevation Model (DEM). In this paper, we propose a novel realistic terrain authoring framework powered by a combination of VAE and generative conditional GAN model. Our framework is an example-based method that attempts to overcome the limitations of existing methods by learning a latent space from a real-world terrain dataset. This latent space allows us to generate multiple variants of terrain from a single input as well as interpolate between terrains while keeping the generated terrains close to real-world data distribution. We also developed an interactive tool that lets the user generate diverse terrains with minimal inputs. We perform a thorough qualitative and quantitative analysis and provide a comparison with other SOTA methods. © 2022 IEEE.

International Geoscience and Remote Sensing Symposium (IGARSS)

Deep Generative Framework for Interactive 3D Terrain Authoring and Manipulation

Existing approaches for 3D garment reconstruction either assume a predefined template for the garment geometry (restricting them to fixed clothing styles) or yield vertex-colored meshes (lacking high-frequency textural details). Our novel framework co-learns geometric and semantic information of garment surface from the input monocular image for template-free textured 3D garment digitization. More specifically, we propose to extend PeeledHuman representation to predict the pixel-Aligned, layered depth and semantic maps to extract 3D garments. The layered representation is further exploited to UV parametrize the arbitrary surface of the extracted garment without any human intervention to form a UV atlas. The texture is then imparted on the UV atlas in a hybrid fashion by first projecting pixels from the input image to UV space for the visible region, followed by inpainting the occluded regions. Thus, we are able to digitize arbitrarily loose clothing styles while retaining high-frequency textural details from a monocular image. We achieve high-fidelity 3D garment reconstruction results on three publicly available datasets and generalization on internet images. © 2022 ACM.

MM 2022 - Proceedings of the 30th ACM International Conference on Multimedia

XCloth: Extracting Template-free Textured 3D Clothes from a Monocular Image

2021 16th IEEE International Conference on Automatic Face and Gesture {\ldots}

AECNet: Attentive EfficientNet For Crowd Counting

The rapid progress in the ease of creating and spreading ultra-realistic media over social platforms calls for an urgent need to develop a generalizable deepfake detection technique. It has been observed that current deepfake generation methods leave discriminative artifacts in the frequency spectrum of fake images and videos. Inspired by this observation, in this paper, we present a novel approach, termed as MD-CSDNetwork, for combining the features in the spatial and frequency domains to mine a shared discriminative representation for classifying \textit{deepfakes}. MD-CSDNetwork is a novel cross-stitched network with two parallel branches carrying the spatial and frequency information, respectively. We hypothesize that these multi-domain input data streams can be considered as related supervisory signals. The supervision from both branches ensures better performance and generalization. Further, the concept of cross-stitch connections is utilized where they are inserted between the two branches to learn an optimal combination of domain-specific and shared representations from other domains automatically. Extensive experiments are conducted on the popular benchmark dataset namely FaceForeniscs++ for forgery classification. We report improvements over all the manipulation types in FaceForensics++ dataset and comparable results with state-of-the-art methods for cross-database evaluation on the Celeb-DF dataset and the Deepfake Detection Dataset.

MD-CSDNetwork: Multi-Domain Cross Stitched Network for Deepfake Detection

Vertex-deletion problems have been at the heart of parameterized complexity throughout its history. Here, the aim is to determine the minimum size (denoted by modℋ) of a modulator to a graph class ℋ, i.e., a set of vertices whose deletion results in a graph in ℋ. Recent years have seen the development of a research programme where the complexity of modulators is measured in ways other than size. For instance, for a graph class ℋ, the graph parameters elimination distance to ℋ (denoted by edℋ) [Bulian and Dawar, Algorithmica, 2016] and ℋ-treewidth (denoted by twℋ) [Eiben et al. JCSS, 2021] aim to minimize the treedepth and treewidth, respectively, of the "torso"of the graph induced on a modulator to the graph class ℋ. Here, the torso of a vertex set S in a graph G is the graph with vertex set S and an edge between two vertices u, v S if there is a path between u and v in G whose internal vertices all lie outside S. In this paper, we show that from the perspective of (non-uniform) fixed-parameter tractability (FPT), the three parameters described above give equally powerful parameterizations for every hereditary graph class ℋ that satisfies mild additional conditions. In fact, we show that for every hereditary graph class ℋ satisfying mild additional conditions, with the exception of edℋ parameterized by twℋ, for every pair of these parameters, computing one parameterized by itself or any of the others is FPT-equivalent to the standard vertex-deletion (to ℋ) problem. As an example, we prove that an FPT algorithm for the vertex-deletion problem implies a non-uniform FPT algorithm for computing edℋ and twℋ. The conclusions of non-uniform FPT algorithms being somewhat unsatisfactory, we essentially prove that if ℋ is hereditary, union-closed, CMSO-definable, and (a) the canonical equivalence relation (or any refinement thereof) for membership in the class can be efficiently computed, or (b) the class admits a "strong irrelevant vertex rule", then there exists a uniform FPT algorithm for edℋ. Using these sufficient conditions, we obtain uniform FPT algorithms for computing edℋ, when ℋ is defined by excluding a finite number of connected (a) minors, or (b) topological minors, or (c) induced subgraphs, or when ℋ is any of bipartite, chordal or interval graphs. For most of these problems, the existence of a uniform FPT algorithm has remained open in the literature. In fact, for some of them, even a non-uniform FPT algorithm was not known. For example, Jansen et al. [STOC 2021] ask for such an algorithm when ℋ is defined by excluding a finite number of connected topological minors. We resolve their question in the affirmative. Copyright © 2022 by SIAM.

Proceedings of the Annual ACM-SIAM Symposium on Discrete Algorithms

Deleting, Eliminating and Decomposing to Hereditary Classes Are All FPT-Equivalent

Traditionally, video conferencing is a widely adopted solution for remote communication, but a lack of immersiveness comes inherently due to the 2D nature of facial representation. The integration of Virtual Reality (VR) in a communication/telepresence system through Head Mounted Displays (HMDs) promises to provide users with a much better immersive experience. However, HMDs cause hindrance by blocking the facial appearance and expressions of the user. We propose a novel attention-enabled encoder-decoder architecture for HMD de-occlusion to overcome these issues. We also propose to train our person-specific model using short videos of the user, captured in varying appearances, and demonstrated generalization to unseen poses and appearances of the user. We report superior qualitative and quantitative results over state-of-the-art methods. We also present applications of this approach to hybrid video teleconferencing using existing animation and 3D face reconstruction pipelines. Dataset is available at this website. © 2022 IEEE.