I am a Ph.D. researcher in Computer Science and Engineering at IIT Gandhinagar, working under the guidance of Prof. Shanmuganathan Raman. My research focuses on computer vision, generative models, image restoration, and hyperspectral imaging, with particular interest in generative priors, latent-space optimization, Gaussian splatting, image restoration, and hyperspectral image denoising and super-resolution.

Before joining IIT Gandhinagar, I worked as a Project Associate at IIT Ropar, where I worked on computer vision and interdisciplinary sensing problems. I completed my M.Tech. in Computer Science and Engineering from Aliah University, Kolkata, graduating second overall, and my B.Tech. from the same university, graduating first overall. I also hold a UAV Pilot Licence for platforms up to 25 kg.

During my Ph.D., I have worked on a range of computer vision and computational imaging problems, with a focus on developing robust methods for real-world image restoration and understanding. My research explores generative models, latent-space optimization, Gaussian splatting, and hyperspectral image processing, with applications in image denoising, deblurring, inpainting, spectral reconstruction, and super-resolution. I also spent six months at the Helmholtz-Zentrum Dresden-Rossendorf: HZDR through the Research Lab Abroad Fellowship, where I further worked on computer vision and imaging problems involving real-world data.

News

Research & Professional Experience

Academic Snapshot

Selected work spanning generative restoration, aerial imaging, scientific data and applied machine learning.

GenR: Robust Generative Face Image Restoration in Latent Space

Akbar Ali, Indra Deep Mastan, Shanmuganathan Raman.

Pattern Recognition Letters, Elsevier — 2026

paper code

A degradation-agnostic face restoration method that optimises in the latent space of a pretrained generator, handling denoising, deblurring and inpainting without retraining per degradation.

Unsupervised Image Deblurring in Latent Space using Pivotal Tuning Inversion

Akbar Ali, Indra Deep Mastan, Shanmuganathan Raman.

Under review — 2026

Pivotal tuning inversion anchors a blurred observation to a generator's latent manifold, recovering sharp detail without paired supervision or a known blur kernel.

ZS-CLIP2Clean: Zero-Shot CLIP-Guided Training-Free Single-Image Denoising

Abhiyodaya Pandey, Akbar Ali, Indra Deep Mastan, Shanmuganathan Raman.

Under review — 2026

Denoising a single image with no training and no clean reference, using CLIP as a semantic critic to steer restoration towards a perceptually faithful result.

InscriptionOCR: A Dataset and Method for Understanding Inscriptions

Jaidev Sanjay Khalane, Akbar Ali, V. N. Prabhakar, Shanmuganathan Raman.

Under review — 2026

A dataset and recognition pipeline for historical stone inscriptions, where weathering and archaic glyph forms break standard scene-text OCR.

Investigating Robustness of Unsupervised StyleGAN Image Restoration

Akbar Ali, Indra Deep Mastan, Shanmuganathan Raman.

IEEE ICIP — 2025

paper data

A stress test of unsupervised StyleGAN restoration under degradations it was never tuned for, showing where latent-space optimisation holds up and where it silently fails.

COT-AD: Cotton Analysis Dataset

Akbar Ali, Pankaj Khanna, Subramanian Sankaranarayanan, Shanmuganathan Raman.

IEEE ICIP — 2025

paper data

An aerial and ground image dataset covering a full cotton growth cycle from weekly drone missions at 10 m, 15 m and 115 m, for crop health and pest analysis.

Descriptive Predictive Model for Parkinson's Disease Analysis

Akbar Ali, Ranjit Kumar Rout, Saiyed Umer.

Springer Nature — 2023

paper

A predictive framework for Parkinson's disease analysis pairing classification accuracy with descriptive feature analysis so clinicians can see which measurements drive each prediction.

My teaching combines fundamentals with hands-on computation and field experience. I particularly enjoy helping students turn an abstract method into something they can implement, visualize and test.

Teaching Focus

Teaching Experience

Lead Teaching Assistant — ES 113, Data Centric Computing

Jan — Apr 2025

IIT Gandhinagar

The course introduces students to the practical foundations of working with data. Topics included data structures and algorithms, Python programming with Pandas and Matplotlib, SQL, data manipulation and introductory machine-learning workflows. As lead TA, I coordinated a 45-student TA team, helped establish the QA-session format and maintained consistent grading standards.

Graduate Teaching Fellow — FP 602, Writing

Aug — Nov 2024

IIT Gandhinagar

This course focuses on developing clear and effective academic and technical writing. I guided 35 students through classwork and assessments, helped them improve the structure and communication of their writing, tracked progress and conducted individual reviews with students who needed additional support.

Teaching Assistant — SC 333, Drone Data Acquisition and Processing

June 2024

IIT Gandhinagar

This hands-on course introduces students to drone-based data acquisition and the processing of imagery collected in the field. I ran flight-training and field sessions for around 30 students, covering pre-flight checks, mission preparation, responsible airspace practices, acquisition procedures and field safety.

Teaching Assistant — ES 114, Probability, Statistics and Data Visualization

Dec 2022 — Apr 2024

IIT Gandhinagar

This course develops the statistical foundations needed for analysing and communicating data. I ran laboratories and tutorials for 50+ students across three semesters, using Python to demonstrate probability, descriptive and inferential statistics, data analysis and effective data visualization.

Student Mentoring

Ongoing

IIT Gandhinagar

Supervise B.Tech and M.Tech students on hyperspectral imaging, image editing and GAN inversion. Two collaborations became co-authored submissions.

Selected media coverage of my research and academic activities.

From generative image restoration to hyperspectral sensing, my projects combine representation learning with real-world data and interdisciplinary collaboration.

Current Research Directions

Collaborations & Field Work

3D Geophysical Image Translation using GANs

Feb 2024 — Jan 2025

A year-long collaboration with geoscientists, translating 3D geophysical scans into photorealistic virtual outcrop geology.

What this involved

Interdisciplinary problem formulation, generative modelling and communication between geological interpretation and computer-vision representations.

Smart Farming of Cotton using Aerial Imagery — COT-AD

Jun 2023 — Jan 2024

Designed and ran a six-month acquisition campaign with agricultural researchers, flying weekly missions at 10 m, 15 m and 115 m. I owned the flight schedule, the multi-altitude protocol, and the dataset that became COT-AD.

Why the dataset matters

The repeated multi-altitude observations follow the same field across a full cotton growth cycle, connecting acquisition strategy with downstream visual analysis.

Drone and Core Data Acquisition — Earth Science, IIT Gandhinagar

2023 — 2024

Planned and led three multi-day campaigns for aerial and core sample collection. Site names withheld for confidentiality.

3D Vision Summer School — IIIT Bangalore

Jun 2024

Week-long school on deep learning for 3D vision. The Gaussian splatting sessions shaped the direction my hyperspectral work took afterwards.

Visvesvaraya PhD Scheme Workshop — IIT Mandi

May 2024

Presented my work to an interdisciplinary audience of scholars from across engineering disciplines.

Selected academic distinctions, fellowships and professional certifications.