We propose a statistical consistency attack (StatAttack) against diverse DeepFake detectors.

We propose the shadow-guided inpainting task to take advantage of the shadow removal and image inpainting.

The open-source tool for building high-quality datasets and computer vision models

We propose a novel data augmentation by enriching the backgrounds for change detection in a weakly-superivsed way.

We propose a shadow-removal benchmark dataset (i.e., SHAREL) to explore the mutual influence of shadow removal and facial landmark detection tasks.

Official implementation of "Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection" in CVPR 2022.

We proposed a novel framework for image inpainting. https://arxiv.org/abs/2107.04281

We propose a new method for effective shadow removal by regarding it as an exposure fusion problem.

Visual tracking library based on PyTorch.

we propose EfficientDerain for high-efficiency single-image deraining

Homepage of Qing Guo