Please visit Google scholar for the full list of publications.
|
Efficient Linear Attention for Fast and Accurate Keypoint Matching
ICMR 2022 [Paper] [Official Page] Recently Transformers have provided state-of-the-art performance in sparse matching, crucial to realize high-performance 3D vision applications. Yet, these Transformers lack efficiency due to the quadratic computational complexity of their attention mechanism. To solve this problem, we propose a new attentional aggregation that achieves high accuracy by aggregating both the global and local information from sparse keypoints. To further improve the efficiency, we propose the joint learning of feature matching and description. Our learning enables simpler and faster matching than Sinkhorn, often used in matching the learned descriptors from Transformers. Contributions:
|
|
Learning of low-level feature keypoints for accurate and robust detection
WACV2021 [Offical publication] [Video] Joint learning of feature descriptor and detector has offered promising 3D reconstruction results; however, they often lack the low-level feature awareness, which causes low accuracy in matched keypoint locations. To address these problems, we propose the supervised learning of keypoint detection with low-level features. Our detector is a single CNN layer extended from the descriptor backbone, which can be jointly learned with the descriptor for maximizing the descriptor matching. This results in the reduction in reprojection error on 3D reconstruction and high accuracy in keypoint detection and matching on HPatach. Contributions:
|
Adaptive Markov Random Fields for Structured Compressive Sensing Ph.D. Thesis, 2019
Others
S. Suwanwimolkul, J. Songsiri, P. Sermwuthisarn, and S. Auethavekiat, “L1 Norm of High Frequency Components as a Regularization Term for Compressed Sensing Reconstruction of Image Signals,” in 2012 IEEE International Symposiumon Intelligent Signal Processing and Communication Systems (ISPACS), New Taipei, Taiwan, 2012, pp. 290-295.
S. Suwanwimolkul, P. Sermwuthisarn, and S. Auethavekiat, “Greedy Steep Slope Finder: the Fast Impulsive Noise Rejection for Compressed Measurement Image Signals,” in 2012 IEEE International Symposiumon Intelligent Signal Processing and Communication Systems (ISPACS), New Taipei, Taiwan, 2012, pp. 296-301.
S. Suwanwimolkul, P. Sermwuthisarn, and S. Auethavekiat, “Greedy Gap’s Boundary Finder: the Impulsive Noise Rejection for Compressed Measurement Image Signals,” in the 12th IEEE International Symposium on Communications and Information Technologies (ISCIT), Gold Coast, Australia, 2012, pp. 798-809.
A Binary Search Algorithm for Impulsive Noise Removal in Compressed Sensing Reconstruction Master Thesis, 2012