Publications and Patents
Managing Noise in labels for Machine Vision at low computational cost
Patent filed
An unsupervised depth-based technique integrated with gradient calculation for reducing noise in industry operator annotations
MMVC: Learned Multi-Mode Video Compression with Block-based Prediction Mode Selection and Density-Adaptive Entropy Coding
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Proposed a novel multi-mode block-based video compression techniques that can acheive high compression ratios.
View PaperEnd-to-end deep learning-based fringe projection framework for 3D profiling of objects
Comput. Vis. Image Underst Journal. 199: 103023 (2020)
Developed a end-to-end deep learning model to profile the 3D shape of objects from structured light images.
View Paper