Search Results for author: Avinash Sharma

Found 18 papers, 4 papers with code

Facial De-occlusion Network for Virtual Telepresence Systems

no code implementations23 Oct 2022 Surabhi Gupta, Ashwath Shetty, Avinash Sharma

Virtual presence is a promising direction in communication and recreation for the future.

Image Inpainting

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

no code implementations27 Aug 2022 Astitva Srivastava, Chandradeep Pokhariya, Sai Sagar Jinka, Avinash Sharma

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).

N2NSkip: Learning Highly Sparse Networks using Neuron-to-Neuron Skip Connections

no code implementations7 Aug 2022 Arvind Subramaniam, Avinash Sharma

Following a preliminary pruning step, N2NSkip connections are randomly added between individual neurons/channels of the pruned network, while maintaining the overall sparsity of the network.

Network Pruning

SHARP: Shape-Aware Reconstruction of People in Loose Clothing

no code implementations24 May 2022 Sai Sagar Jinka, Astitva Srivastava, Chandradeep Pokhariya, Avinash Sharma, P. J. Narayanan

The parametric body prior enforces geometrical consistency on the body shape and pose, while the non-parametric representation models loose clothing and handle self-occlusions as well.

Deep Generative Framework for Interactive 3D Terrain Authoring and Manipulation

1 code implementation7 Jan 2022 Shanthika Naik, Aryamaan Jain, Avinash Sharma, KS Rajan

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.

Attention based Occlusion Removal for Hybrid Telepresence Systems

no code implementations2 Dec 2021 Surabhi Gupta, Ashwath Shetty, Avinash Sharma

Traditionally, video conferencing is a widely adopted solution for telecommunication, but a lack of immersiveness comes inherently due to the 2D nature of facial representation.

3D Face Reconstruction

3D Shape Registration Using Spectral Graph Embedding and Probabilistic Matching

no code implementations21 Jun 2021 Avinash Sharma, Radu Horaud, Diana Mateus

We discuss solutions for the exact and inexact graph isomorphism problems and recall the main spectral properties of the combinatorial graph Laplacian; We provide a novel analysis of the commute-time embedding that allows us to interpret the latter in terms of the PCA of a graph, and to select the appropriate dimension of the associated embedded metric space; We derive a unit hyper-sphere normalization for the commute-time embedding that allows us to register two shapes with different samplings; We propose a novel method to find the eigenvalue-eigenvector ordering and the eigenvector signs using the eigensignature (histogram) which is invariant to the isometric shape deformations and fits well in the spectral graph matching framework, and we present a probabilistic shape matching formulation using an expectation maximization point registration algorithm which alternates between aligning the eigenbases and finding a vertex-to-vertex assignment.

Dimensionality Reduction Graph Embedding +1

Reconstruction of People in Loose Clothing

no code implementations9 Jun 2021 Sai Sagar Jinka, Rohan Chacko, Astitva Srivastava, Avinash Sharma, P. J. Narayanan

3D human body reconstruction from monocular images is an interesting and ill-posed problem in computer vision with wider applications in multiple domains.

GlocalNet: Class-aware Long-term Human Motion Synthesis

no code implementations19 Dec 2020 Neeraj Battan, Yudhik Agrawal, Veeravalli Saisooryarao, Aman Goel, Avinash Sharma

Synthesis of long-term human motion skeleton sequences is essential to aid human-centric video generation with potential applications in Augmented Reality, 3D character animations, pedestrian trajectory prediction, etc.

Motion Synthesis Pedestrian Trajectory Prediction +2

AFN: Attentional Feedback Network based 3D Terrain Super-Resolution

1 code implementation4 Oct 2020 Ashish Kubade, Diptiben Patel, Avinash Sharma, K. S. Rajan

Terrain, representing features of an earth surface, plays a crucial role in many applications such as simulations, route planning, analysis of surface dynamics, computer graphics-based games, entertainment, films, to name a few.

Super-Resolution

Feedback Neural Network based Super-resolution of DEM for generating high fidelity features

no code implementations3 Jul 2020 Ashish Kubade, Avinash Sharma, K S Rajan

High resolution Digital Elevation Models(DEMs) are an important requirement for many applications like modelling water flow, landslides, avalanches etc.

Image Super-Resolution

PeeledHuman: Robust Shape Representation for Textured 3D Human Body Reconstruction

1 code implementation16 Feb 2020 Sai Sagar Jinka, Rohan Chacko, Avinash Sharma, P. J. Narayanan

We introduce PeeledHuman - a novel shape representation of the human body that is robust to self-occlusions.

3D Reconstruction

HumanMeshNet: Polygonal Mesh Recovery of Humans

2 code implementations19 Aug 2019 Abbhinav Venkat, Chaitanya Patel, Yudhik Agrawal, Avinash Sharma

3D Human Body Reconstruction from a monocular image is an important problem in computer vision with applications in virtual and augmented reality platforms, animation industry, en-commerce domain, etc.

Surface Reconstruction

DeepHuMS: Deep Human Motion Signature for 3D Skeletal Sequences

no code implementations15 Aug 2019 Neeraj Battan, Abbhinav Venkat, Avinash Sharma

3D Human Motion Indexing and Retrieval is an interesting problem due to the rise of several data-driven applications aimed at analyzing and/or re-utilizing 3D human skeletal data, such as data-driven animation, analysis of sports bio-mechanics, human surveillance etc.

Retrieval

Deep Textured 3D Reconstruction of Human Bodies

no code implementations18 Sep 2018 Abbhinav Venkat, Sai Sagar Jinka, Avinash Sharma

In this paper, we propose a deep learning based solution for textured 3D reconstruction of human body shapes from a single view RGB image.

3D Reconstruction

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