Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision

1 code implementation • CVPR 2023 • Xinyi Ying, Li Liu, Yingqian Wang, Ruojing Li, Nuo Chen, Zaiping Lin, Weidong Sheng, Shilin Zhou

Interestingly, during the training phase supervised by point labels, we discover that CNNs first learn to segment a cluster of pixels near the targets, and then gradually converge to predict groundtruth point labels.

Local Motion and Contrast Priors Driven Deep Network for Infrared Small Target Super-Resolution

1 code implementation • 4 Jan 2022 • Xinyi Ying, Yingqian Wang, Longguang Wang, Weidong Sheng, Li Liu, Zaiping Lin, Shilin Zhou

Specifically, motivated by the local motion prior in the spatio-temporal dimension, we propose a local spatio-temporal attention module to perform implicit frame alignment and incorporate the local spatio-temporal information to enhance the local features (especially for small targets).

Super-Resolution

Deformable 3D Convolution for Video Super-Resolution

1 code implementation • 6 Apr 2020 • Xinyi Ying, Longguang Wang, Yingqian Wang, Weidong Sheng, Wei An, Yulan Guo

In this paper, we propose a deformable 3D convolution network (D3Dnet) to incorporate spatio-temporal information from both spatial and temporal dimensions for video SR.

Motion Compensation Video Super-Resolution