Moushumi Medhi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Moushumi Medhi has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
Aradhana Dandautiya
CSIR-Central Electronics Engineering Research Institute, Pilani, India
1 shared publicationJagdish Lal Raheja
CSIR-Central Electronics Engineering Research Institute, Pilani, India
1 shared publicationRajiv Ranjan Sahay
Indian Institute of Technology Kharagpur
1 shared publication- Rajiv Ranjan Sahay
Indian Institute of Technology Kharagpur
1 shared publication - Rajiv Ranjan Sahay
Indian Institute of Technology, Kharagpur
1 shared publication - Rajiv Ranjan Sahay
Department of Electrical Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India
1 shared publication
Latest Publications
- 7 January 2025
- Published by Springer Nature in Machine Vision and Applications
- Vol. 36 (2) , 1-30
Adversarial learning for unguided single depth map completion of indoor scenes
- 7 January 2025
- Published by Springer Nature in Machine Vision and Applications
- Vol. 36 (2) , 1-30
Adversarial learning for unguided single depth map completion of indoor scenes
- Open Access
- 17 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (2s) , 1-26
Distill-DBDGAN: Knowledge Distillation and Adversarial Learning Framework for Defocus Blur Detection
Defocus blur detection (DBD) aims to segment the blurred regions from a given image affected by defocus blur. It is a crucial pre-processing step for various computer vision tasks. With the increasing popularity of small mobile devices, there is a need for a computationally efficient method to detect defocus blur accurately. We propose an efficient defocus blur detection method that estimates the probability of each pixel being focused or blurred in resource-constraint devices. Despite remarkable advances made by the recent deep learning-based methods, they still suffer from several challenges such as background clutter, scale sensitivity, indistinguishable low-contrast focused regions from out-of-focus blur, and especially high computational cost and memory requirement. To address the first three challenges, we develop a novel deep network that efficiently detects blur map from the input blurred image. Specifically, we integrate multi-scale features in the deep network to resolve the scale ambiguities and simultaneously modeled the non-local structural correlations in the high-level blur features. To handle the last two issues, we eventually frame our DBD algorithm to perform knowledge distillation by transferring information from the larger teacher network to a compact student network. All the networks are adversarially trained in an end-to-end manner to enforce higher order consistencies between the output and the target distributions. Experimental results demonstrate the state-of-the-art performance of the larger teacher network, while our proposed lightweight DBD model imitates the output of the teacher network without significant loss in accuracy. The codes, pre-trained model weights, and the results will be made publicly available.
- 17 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (2s) , 1-26
Open AccessDistill-DBDGAN: Knowledge Distillation and Adversarial Learning Framework for Defocus Blur Detection
Defocus blur detection (DBD) aims to segment the blurred regions from a given image affected by defocus blur. It is a crucial pre-processing step for various computer vision tasks. With the increasing popularity of small mobile devices, there is a need for a computationally efficient method to detect defocus blur accurately. We propose an efficient defocus blur detection method that estimates the probability of each pixel being focused or blurred in resource-constraint devices. Despite remarkable advances made by the recent deep learning-based methods, they still suffer from several challenges such as background clutter, scale sensitivity, indistinguishable low-contrast focused regions from out-of-focus blur, and especially high computational cost and memory requirement. To address the first three challenges, we develop a novel deep network that efficiently detects blur map from the input blurred image. Specifically, we integrate multi-scale features in the deep network to resolve the scale ambiguities and simultaneously modeled the non-local structural correlations in the high-level blur features. To handle the last two issues, we eventually frame our DBD algorithm to perform knowledge distillation by transferring information from the larger teacher network to a compact student network. All the networks are adversarially trained in an end-to-end manner to enforce higher order consistencies between the output and the target distributions. Experimental results demonstrate the state-of-the-art performance of the larger teacher network, while our proposed lightweight DBD model imitates the output of the teacher network without significant loss in accuracy. The codes, pre-trained model weights, and the results will be made publicly available.
- 24 July 2022
- Published by Springer Nature
- p. 504-515
Deep Two-Stage LiDAR Depth Completion
- 1 July 2019
- Published by Springer Nature in Journal of Nondestructive Evaluation
- Vol. 38 (3) , 1-16
Real-Time Video Surveillance Based Structural Health Monitoring of Civil Structures Using Artificial Neural Network
- 1 July 2019
- Published by Springer Nature in Journal of Nondestructive Evaluation
- Vol. 38 (3) , 1-16
Real-Time Video Surveillance Based Structural Health Monitoring of Civil Structures Using Artificial Neural Network
- 21 October 2017
- Published by Springer Nature
- p. 145-156
A Text Recognition Augmented Deep Learning Approach for Logo Identification
- 21 October 2017
- Published by Springer Nature
- p. 145-156
A Text Recognition Augmented Deep Learning Approach for Logo Identification