baolp

demoireing_with_focused_and_defocused_images_pairs

DocTr

Code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”. ACM MM, 2021.

SPANet

Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset (CVPR'19)

TransTPS

VAL-PAT

Learning Transferable Pedestrian Representation from Multimodal Information Supervision

vision

Datasets, Transforms and Models specific to Computer Vision

baolp/demoireing_with_focused_and_defocused_images_pairs

baolp/VAL-PAT

Learning Transferable Pedestrian Representation from Multimodal Information Supervision

baolp/TransTPS

baolp/DocTr

Code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”. ACM MM, 2021.

baolp/SPANet

Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset (CVPR'19)

baolp/vision

Datasets, Transforms and Models specific to Computer Vision