• Publications
  • Influence
AOD-Net: All-in-One Dehazing Network
TLDR
An image dehazing model built with a convolutional neural network (CNN) based on a re-formulated atmospheric scattering model, called All-in-One Dehazing Network (AOD-Net), which demonstrates superior performance than the state-of-the-art in terms of PSNR, SSIM and the subjective visual quality. Expand
Benchmarking Single-Image Dehazing and Beyond
TLDR
This work presents a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single-Image DEhazing (RESIDE), which highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes. Expand
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
TLDR
It is demonstrated that DeblurGAN-V2 has very competitive performance on several popular benchmarks, in terms of deblurring quality (both objective and subjective), as well as efficiency, and is effective for general image restoration tasks too. Expand
Graph Contrastive Learning with Augmentations
TLDR
The results show that, even without tuning augmentation extents nor using sophisticated GNN architectures, the GraphCL framework can produce graph representations of similar or better generalizability, transferrability, and robustness compared to state-of-the-art methods. Expand
EnlightenGAN: Deep Light Enhancement Without Paired Supervision
TLDR
This paper proposes a highly effective unsupervised generative adversarial network, dubbed EnlightenGAN, that can be trained without low/normal-light image pairs, yet proves to generalize very well on various real-world test images. Expand
UnitBox: An Advanced Object Detection Network
TLDR
A novel Intersection over Union (IoU) loss function for bounding box prediction, which regresses the four bounds of a predicted box as a whole unit, and introduces the UnitBox, which performs accurate and efficient localization, shows robust to objects of varied shapes and scales, and converges fast. Expand
An All-in-One Network for Dehazing and Beyond
TLDR
This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net), designed based on a re-formulated atmospheric scattering model that directly generates the clean image through a light-weight CNN. Expand
AutoGAN: Neural Architecture Search for Generative Adversarial Networks
TLDR
This paper presents the first preliminary study on introducing the NAS algorithm to generative adversarial networks (GANs), dubbed AutoGAN, and discovers architectures that achieve highly competitive performance compared to current state-of-the-art hand-crafted GANs. Expand
Robust Video Super-Resolution with Learned Temporal Dynamics
TLDR
This work proposes a temporal adaptive neural network that can adaptively determine the optimal scale of temporal dependency and reduces the complexity of motion between neighboring frames using a spatial alignment network which is much more robust and efficient than competing alignment methods. Expand
...
1
2
3
4
5
...