Due to limited camera capacities, digital images usually have a narrower...
Neural Radiance Field (NeRF) is a promising approach for synthesizing no...
This paper proposes a new framework for low-light image enhancement by
s...
Plant leaf identification is crucial for biodiversity protection and
con...
Existing learning-based methods for point cloud rendering adopt various ...
Synthesizing photo-realistic images from a point cloud is challenging be...
The fidelity of Generative Adversarial Networks (GAN) inversion is imped...
Deep Neural Networks (DNNs) are vulnerable to the black-box adversarial
...
Inspired by the ability of deep generative models to generate highly
rea...
Unsupervised domain adaptation in semantic segmentation has been raised ...
Existing automatic data augmentation (DA) methods either ignore updating...
Despite the quality improvement brought by the recent methods, video
sup...
To facilitate video denoising research, we construct a compelling datase...
Cross-domain few-shot learning (CDFSL) remains a largely unsolved proble...
Due to the vulnerability of deep neural networks (DNNs) to adversarial
e...
To synthesize a realistic action sequence based on a single human image,...
Adversarial training is promising for improving robustness of deep neura...
Following the principle of to set one's own spear against one's own shie...