Mr. Inderjeet | Image Restoration | Best Researcher Award
Research Scholar | Indian Institute of Technology Ropar | India
Inderjeet is a research scholar in the Department of Electrical Engineering at the Indian Institute of Technology Ropar, specializing in computer vision, video and image processing, deep learning, and image restoration and enhancement. His doctoral research focuses on developing deep learning-based approaches for single-image super-resolution, where he has proposed several innovative architectures including recurrent, transformer-based, and generative models. He has authored journal and conference publications in leading venues, contributing to advancements in low-level vision tasks such as super-resolution, dehazing, inpainting, and low-light enhancement. His work integrates convolutional neural networks, recurrent models, vision transformers, and generative adversarial networks with a focus on improving visual fidelity, efficiency, and robustness. In addition to his research contributions, he has mentored M.Tech., B.Tech., and internship students on projects spanning cataract detection, plant disease classification, image depth estimation, and image restoration, demonstrating his commitment to academic leadership and collaborative research. His technical expertise extends across machine learning algorithms, optimization, and statistical modeling, supported by strong programming skills in Python and MATLAB. He has also worked on filter design and optimization problems during his postgraduate studies, proposing efficient methods for FIR-to-IIR filter approximation using metaheuristic approaches. His research achievements have been recognized with prestigious fellowships and scholarships, and his scholarly impact is reflected in 2 citations across 2 documents and 6 total publications, underscoring his academic excellence and sustained commitment to innovation in image and vision computing. With a growing portfolio of impactful research, mentorship, and publications, he continues to explore deep learning methodologies that advance the state of the art in computer vision and support the development of practical artificial intelligence solutions for real-world applications.
Featured Publications
Inderjeet, & Sahambi, J. S. (2026). RMRDN: Recurrent multi-receptive residual dense network for image super-resolution. Digital Signal Processing, 145, 105556.
Inderjeet, & Sahambi, J. S. (2025). CMOA-Net: Competent multi-observant attention network for single-image super-resolution. IEEE Transactions on Emerging Topics in Computational Intelligence.
Inderjeet, & Sahambi, J. S. (2025). RMRDN: Recurrent multi-receptive residual dense network for image super-resolution. SSRN.
Inderjeet, & Sahambi, J. S. (2025, May 13). GAMSRN: Global attention multi-scale residual network for single-image super-resolution and low-light enhancement. 2025 National Conference on Communications (NCC).
Inderjeet, & Sahambi, J. S. (2024). Efficient contextual feature network for single image super resolution. In Advances in Intelligent Systems and Computing (pp. xxx–xxx). Springer.