Mohammad Zohaib

I am a postdoctoral researcher at PAVIS, Istituto Italiano di Tecnologia (IIT), Genova, Italy, working with Dr. Alessio Del Bue. I am working on a research problem, estimating the 3D keypoints for deformable objects in a self-supervised way.

I have done my PhD from the same (PAVIS) lab on March 27th, 2023, where I have desinged deep leanring networks to estimate 3D keypoints for rigid objects considering 2D and 3D data.

my_page@IIT  /  LinkedIn  /  Google Scholar  /  Github  /  Google-site  /  Email

profile photo
Selected Publications

Preview coming soon
SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapes
Mohammad Zohaib, Luca Cosmo, Alessio Del Bue
ECCV, 2024
PDF / Code [Coming soon...]

The paper introduces "SelfGeo", a self-supervised method for estimating persistent 3D keypoints on deformable shapes without requiring human annotations. This generalized approach is broadly applicable, without being limited to specific shapes.

Preview coming soon
SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data
Mohammad Zohaib, Alessio Del Bue
ICCV, 2023
PDF / Code

The paper presents a self-supervised approach to estimate 3D keypoints that are semantically coherent, proximal to PCD surface and resilient to PCD perturbations.

Preview coming soon
CDHN: Cross-Domain Hallucination Network For 3D Key-points Estimation”, Pattern Recognition
Mohammad Zohaib, Milind G. Padalkar, Pietro Morerio, Matteo Taiana, Alessio Del Bue
Pattern Recognition, 2023 , Under review
PDF

The paper presents a teacher-student network that hallucinates 3D features directly from RGB images to improve the keypoints localization.

Preview coming soon
Preview coming soon
A featureless approach for object detection and tracking in dynamic environments
Mohammad Zohaib, Muhammad Ahsan Mudassir Khan Jamshed Iqbal
Public Library of Science (PLoS) ONE journal, 2023
PDF /

This work presents a ROS-based algorithm for constructing dynamic maps, which exploits the spatial-temporal locality for detecting and tracking moving objects without relying on prior knowledge of their geometrical features.

Preview coming soon
3D Key-points Estimation From Single-view RGB Images
Mohammad Zohaib, Matteo Taiana, Milind G. Padalkar, Alessio Del Bue
ICIAP, 2022 [Oral presentation]
PDF / Sup. Material / Video

Our paper presents an end-to-end approach that leverages single-view RGB images for estimating an ordered list of 3D keypoints.

Preview coming soon
Towards Reconstruction of 3D Shapes in a Realistic Environment
Mohammad Zohaib, Matteo Taiana, Alessio Del Bue
ICIAP, 2022
PDF / Sup. Material / Poster / Video

Our paper presents an end-to-end 3D reconsturction approach that learns to compute stable features for an object by reducing the influence of image background.

Preview coming soon
Preview coming soon
An Autonomous Seeder for Maize Crop
Amir Asghar Ali, Mohammad Zohaib, Syed Atif Mehdi
ICRAI, 2019
PDF

The paper presents an autonomous seeder robot that minimizes human involvement in the sowing process; thus, it reduces errors and time consumption and increases efficiency.


Website built using source code provided by Jon Barron.

Last updated on: