Noisy labels are commonly found in real-world data, which cause performance degradation of deep neural networks.
This paper presents WaveFill, a wavelet-based inpainting network that decomposes images into multiple frequency bands and fills the missing regions in each frequency band separately and explicitly.
Accurate lighting estimation is challenging yet critical to many computer vision and computer graphics tasks such as high-dynamic-range (HDR) relighting.
In addition, we design a semantic-activation normalization scheme that injects style features of exemplars into the image translation process successfully.
Experimental results show that our method can generate high-quality alpha mattes for various videos featuring appearance change, occlusion, and fast motion.
HRP requires that more attention should be paid to human regions, while GLC requires that a group of portrait photos should be retouched to a consistent tone.
The proposed GAN prior embedded network (GPEN) is easy-to-implement, and it can generate visually photo-realistic results.
Ranked #1 on Blind Face Restoration on CelebA-HQ
With image-level attention, transformers enable to model long-range dependencies and generate diverse contents with autoregressive modeling of pixel-sequence distributions.
The existence of noisy labels in real-world data negatively impacts the performance of deep learning models.
This paper presents Geometric Mover's Light (GMLight), a lighting estimation framework that employs a regression network and a generative projector for effective illumination estimation.
This paper proposes a novel active boundary loss for semantic segmentation.
Motivated by the Earth Mover distance, we design a novel spherical mover's loss that guides to regress light distribution parameters accurately by taking advantage of the subtleties of spherical distribution.
State-of-the-art methods strive to harmonize the composed image by adapting the style of foreground objects to be compatible with the background image, whereas the potential shadow of foreground objects within the composed image which is critical to the composition realism is largely neglected.
Recent advances in generative adversarial networks (GANs) have achieved great success in automated image composition that generates new images by embedding interested foreground objects into background images automatically.
The ability to produce convincing textural details is essential for the fidelity of synthesized person images.
Ranked #2 on Pose Transfer on Deep-Fashion
In this paper, we propose to use coarse annotated data coupled with fine annotated data to boost end-to-end semantic human matting without trimaps as extra input.
Ranked #8 on Image Matting on AM-2K
This paper presents a novel transfer multi-task learning method for Bacteria Biotope rel+ner task at BioNLP-OST 2019.
Video contents have become a critical tool for promoting products in E-commerce.
The proposed model is trained and evaluated on a few publicly available datasets and has achieved the state-of-the-art accuracy with a mean Dice coefficient index of 0. 947 $\pm$ 0. 044.