3DVisLab 3D vision group at CSE@IITJ and CVIT@IIITH
Group Picture

This is a research group led by Dr Avinash Sharma, who has recently moved to Computer Science & Engineering department at IIT Jodhpur as an associate professor while continuing his affiliation with Centre for Visual Information Technology (CVIT), IIIT Hyderabad. We primarily work on the computer vision and machine learning problems with a focus on 3D scene understanding and reconstruction. Specifically, we deal with problems where human body is reconstructed from 2D images and analysed in 3D, generation & analysis of 3D terrains, registration of point clouds of indoor scenes captured from commodity sensors as well as large outdoor scenes captured from LIDAR scanners. Students part of our group have been honored as recipients of prestigious fellowships from Google, Tata Consultancy Services (TCS), and Qualcomm.

We are looking for motivated PhD students and long-term RAs/interns with interest in 3D computer vision to join us. Please check here for more details.

Research Interests


3DHumans: High-Fidelity 3D Scans of People in Diverse Clothing Styles

4DHumans: Temporally Consistent Dynamic Scans of Humans in Motion


WordRobe: Text-Guided Generation of Textured 3D Garments
Astitva Srivastava,Pranav Manu,Amit Raj, Varun Jampani, Avinash Sharma
European Conference on Computer Vision (ECCV) 2024
[Project Page] [Paper]

MANUS: Markerless Hand-Object Grasp Capture using Articulated 3D Gaussians
Chandradeep Pokhariya, Ishaan N Shah, Angela Xing, Zekun Li, Kefan Chen, Avinash Sharma and Srinath Sridhar
Conference on Computer Vision and Pattern Recognition (CVPR) 2024
[Project Page] [Paper]

ATPPNet: Attention based Temporal Point cloud Prediction Network
Kaustab Pal, Aditya Sharma, Avinash Sharma, K. Madhava Krishna
IEEE International Conference on Robotics and Automation (ICRA) 2024
(In collaboration with RRC, IIITH) [Code] [Paper]

Learning Based Infinite Terrain Generation with Level of Detailing
Aryamaan Jain, Avinash Sharma and KS Rajan
International Conference on 3D Vision (3DV) 2024
[Code] [Paper]

Enhanced Spatio-Temporal Context for Temporally Consistent Robust 3D Human Motion Recovery from Monocular Videos
Sushovan Chanda, Amogh Tiwari, Lokender Tiwari, Brojeshwar Bhowmick, Avinash Sharma and Hrishav Barua
Arxiv 2023

CLIP-Head: Text-Guided Generation of Textured Neural Parametric 3D Head Models
Pranav Manu*, Astitva Srivastava* and Avinash Sharma
ACM SIGGRAPH Asia Technical Communications 2023
[Project Page] [Code] [Paper]

ConVol-E: Continuous Volumetric Embeddings for Human-Centric Dense Correspondence Estimation
Amogh Tiwari, Pranav Manu, Nakul Rathore, Astitva Srivastava and Avinash Sharma
CVPR Workshop 2023

SHARP: Shape-Aware Reconstruction of People in Loose Clothing
Sai Sagar Jinka, Astitva Srivastava, Chandradeep Pokhariya, Avinash Sharma and P.J. Narayanan
IJCV 2022
[Project Page] [Paper] [Dataset]

REF-SHARP: REFined face and geometry reconstruction of people in loose clothing
Snehith Goud Routhu, Sai Sagar Jinka and Avinash Sharma

Adaptive & Multi-Resolution Procedural Infinite Terrain Generation with Diffusion Models and Perlin Noise
Aryamaan Jain, Avinash Sharma and K S Rajan
[Project Page] [Code] [Paper] [Presentation]

Discretization-Agnostic Deep Self-Supervised 3D Surface Parameterization
Chandradeep Pokhariya*, Shanthika Naik*, Astitva Srivastava and Avinash Sharma
ACM SIGGRAPH Asia Technical Communications 2022
[Project Page] [Paper] [Supplementary] [Presentation]

Supervision by Landmarks: An Enhanced Facial De-occlusion Network for VR-based Applications
Surabhi Gupta, Sai Sagar Jinka, Avinash Sharma and Anoop Namboodiri
ECCV Workshop 2022

Deep Self-supervised UV Parameterization for Template-free Textured 3D Digitization of Garments
Shanthika Naik*, Chandradeep Pokhariya*, Astitva Srivastava and Avinash Sharma
Preprint 2022

xCloth: Extracting Template-free Textured 3D Clothes from a Monocular Image
Astitva Srivastava, Chandradeep Pokhariya, Sai Sagar Jinka and Avinash Sharma
ACM Multimedia 2022

Robust 3D Garment Digitization from Monocular 2D Images for 3D Virtual Try-On Systems
Sahib Majithia, Sandeep N. Parameswaran, Sadbhavana Babar, Vikram Garg, Astitva Srivastava and Avinash Sharma
WACV 2021

Automated tree generation using grammar & particle system
Aryamaan Jain, Jyoti Sunkara, Ishaan Shah, Avinash Sharma and K S Rajan
[Project Page] [Code] [Paper] [Presentation]

Coarse-to-fine 3D clothed human reconstruction using peeled semantic segmentation context
Snehith Goud Routhu, Sai Sagar Jinka and Avinash Sharma
[Project Page] [Paper]

Attention based Occlusion Removal for Hybrid Telepresence Systems
Surabhi Gupta, Ashwath Shetty, Avinash Sharma
CRV 2022

A-GHN: Attention-based Fusion of Multiple GraphHeat Networks for Structural to Functional Brain Mapping
Subba Reddy Oota, Archi Yadav, Arpita Dash, Surampudi Bapi Raju, Avinash Sharma
bioRxiv 2021

GlocalNet: Class-aware Long-term Human Motion Synthesis
Neeraj Battan, Yudhik Agrawal, Sai Soorya Rao, Aman Goel, Avinash Sharma
WACV 2021

PeeledHuman: Robust Shape Representation for Textured 3D Human Body Reconstruction
Sai Sagar Jinka, Rohan Chacko, Avinash Sharma and P. J. Narayanan
3DV 2020
[Project Page] [Code] [Paper] [Teaser Video]

AFN: Attentional Feedback Network based 3D Terrain Super-Resolution
Ashish Kubade, Diptiben Patel, Avinash Sharma, and K. S. Rajan
ACCV 2020
[Code] [Paper]

Feedback Neural Network based Super-resolution of DEM for generating high fidelity features
Ashish Kubade, Avinash Sharma, K S Rajan

Action Quality Assessment using Siamese Network-Based Deep Metric Learning
Hiteshi Jain, Gaurav Harit, Avinash Sharma

DeepHuMS: Deep Human Motion Signature for 3D Skeletal Sequences
Neeraj Battan, Abbhinav Venkat and Avinash Sharma
ACPR 2019
[Project Page] [Paper] [Teaser Video]

N2NSkip: Learning Highly Sparse Networks using neuron-to-neuron skip connections
Arvind Subramaniam, Avinash Sharma
BMVC 2020
[Project Page] [Code] [Paper]

HumanMeshNet: Polygonal Mesh Recovery of Humans
Abbhinav Venkat, Chaitanya Patel, Yudhik Agrawal and Avinash Sharma
ICCV Workshops 2019
[Project Page] [Code] [Paper] [Teaser Video]

Resting state dynamics meets anatomical structure: Temporal multiple kernel learning (tMKL) model
Sriniwas Govinda Surampudi, Joyneel Misra, Gustavo Deco, Raju Surampudi Bapi, Avinash Sharma, Dipanjan Roy
NeuroImage 2019
[Code] [Paper]

Non-rigid Registration using Spectral Graph Wavelet Features
Alphin J. Thottupattu, Shivin Yadav and Avinash Sharma

SplineNet: B-spline neural network for efficient classification of 3D data
Sai Sagar Jinka and Avinash Sharma
[Project Page] [Paper]

Towards View-Invariant Intersection Recognition from Videos using Deep Network Ensembles
Abhijeet Kumar, Gunshi Gupta, Avinash Sharma and K. Madhav Krishna
IROS 2018

Deep Textured 3D Reconstruction of Human Bodies
Abbhinav Venkat, Sai Sagar Jinka and Avinash Sharma
BMVC 2018
[Project Page] [Paper]

Fast multi model motion segmentation on road scenes
US Mehtab Sandhu, Nazrul Haque, Avinash Sharma, K. Madhav Krishna, Shanti Medasani
IV 2018

MKL Based Local Label Diffusion for Automatic Image Annotation
Abhijeet Kumar, Anjali Shenoy and Avinash Sharma
[Project Page] [Paper]

Multiple Kernel Learning Model for Relating Structural and Functional Connectivity in the Brain
Sriniwas Govinda Surampudi, Shruti Naik, Raju Bapi Surampudi, Viktor K Jirsa, Avinash Sharma, Dipanjan Roy
Scientific reports 2018

Multi-trajectory pose correspondences using scale-dependent topological analysis of pose-graphs
Sayantan Datta, Avinash Sharma and K. Madhava Krishna
IROS 2017

SLAM Pose-Graph Robustification Via Multi-Scale Heat-Kernel Analysis
Sayantan Datta, Siddharth Tourani, Avinash Sharma and K. Madhava Krishna
CDC 2016

Combining Multiscale Diffusion Kernels for Learning the Structural and Functional Brain Connectivity
S. G. Surampudi, S. Naik, A. Sharma, R. B. Surampudi, D. Roy
NIPSW 2016

Image Annotation using Multi-scale Hypergraph Heat Diffusion Framework
Venkatesh N. Murthy, Avinash Sharma, Visesh Chari, and R. Manmatha
ICMR 2016