Maitreya Suin

I am working as a Senior Researcher, AI at Samsung AI Center Toronto. Before that, I was a postdoctoral researcher in the AIEM Lab, Johns Hopkins University. I was advised by Prof. Rama Chellappa specializing in topics related to Computer Vision and Machine Learning. Previously, I completed my MS and PhD at Image Processing and Computer Vision Lab, IIT Madras under the supervision of Prof. A. N. Rajagopalan. My research expertise lies in the domains of computer vision, machine learning, and multimodal generative AI, with a specific focus on diffusion models, vision-language models, post-training, camera image-processing pipelines, image and video restoration, and image/face recognition and detection. My recent work involves leveraging foundation models, including diffusion models and VLM/LLM-based reasoning systems, for tasks such as degradation-aware image-quality analysis, camera-pipeline triage, blind face restoration, and few-shot personalized generation/editing, with an emphasis on perceptual quality, identity preservation, reliability, and efficiency. During my PhD, I focused on building adaptive neural networks for handling spatially and temporally varying tasks, using efficient non-local attention and spatially varying filtering modules for images and videos.

Updates

(2025.07) Our paper “Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration” has been accepted at CVPR 2026.
(2025.07) Our paper “Improved Representation Learning for Unconstrained Face Recognition” has been accepted at the IEEE International Conference on Automatic Face and Gesture Recognition (FG 2025).
(2025.06) Our paper “DiffNat : Exploiting the Kurtosis Concentration Property for Image quality improvement” has been accepted at the Transactions on Machine Learning Research (TMLR).
(2024.04) Our paper “CLR-Face: Conditional Latent Refinement for Blind Face Restoration Using Score-Based Diffusion Models” has been accepted at the International Joint Conference on Artificial Intelligence (IJCAI24).
(2023.11) Our paper “Diffuse and Restore: A Region-Adaptive Diffusion Model for Identity-Preserving Blind Face Restoration” has been accepted at Winter Conference on Applications of Computer Vision, 2024 (WACV).
(2023.09) Our paper “ATDetect: Face Detection and Keypoint Extraction at Range and Altitude” has been accepted at IEEE International Joint Conference on Biometrics, 2023 (IJCB).
(2023.01) Our paper “Illumination-adaptive unpaired low-light enhancement” has been accepted at IEEE Transactions on Circuits and Systems for Video Technology (IEEE-TCSVT).
(2022.08) Our paper “Hybrid Transformer based Feature Fusion for Self-Supervised Monocular Depth Estimation” has been accepted at AIM, ECCV 2022.
(2021.07) Our paper “Distillation-guided Image Inpainting” has been accepted at ICCV 2021 Conference.
(2021.02) Our paper “Gated Spatio-Temporal Attention-Guided Video Deblurring” has been accepted at CVPR 2021 Conference.
(2020.12) Our paper “Degradation Aware Approach to Image Restoration Using Knowledge Distillation” has been accepted at IEEE Journal of Selected Topics in Signal Processing (IEEE-JSTSP).
Check out the articles in @EduMinOfIndia, IITM Tech Talk.
(2020.10) Our team from IPCV Lab, IITM developed Mixed-reality segment for the 2020 Virtual Convocation of IIT Madras.
(2019.11) Our paper “Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring” has been accepted at CVPR 2020 Conference.
I have been awarded Google Travel Grant to present our paper at AAAI 2020 Conference, New York, USA.
(2019.11) Our paper “An efficient Framework for Dense Video Captioning” has been accepted at AAAI 2020 Conference.
(2019.11) Our team won the runner up prizes in ICCV-AIM 2019 Bokeh Effect Challenge and Realistic Image Super-resolution Challenge.
(2019.04) Our team has claimed 1st position in CVPR-NTIRE 2019 Image Colorization Challenge. We are also among the finalists in Image Dehazing challenges of NTIRE 2019.