• Publications
  • Influence
H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes
TLDR
We propose a novel hybrid densely connected UNet, which consists of a 2-D DenseUNet for efficiently extracting intra-slice features and a 3-D counterpart for hierarchically aggregating volumetric contexts under the spirit of the auto-context algorithm for liver and tumor segmentation. Expand
  • 448
  • 35
  • PDF
Underexposed Photo Enhancement Using Deep Illumination Estimation
TLDR
We introduce intermediate illumination in our network to associate the input with expected enhancement result, which augments the network's capability to learn complex photographic adjustment from expert-retouched input/output images. Expand
  • 100
  • 33
  • PDF
Solid texture synthesis from 2D exemplars
TLDR
We present a novel method for synthesizing solid textures from 2D texture exemplars by combining non-parametric texture optimization with histogram matching. Expand
  • 191
  • 32
  • PDF
Direction-Aware Spatial Context Features for Shadow Detection
TLDR
This paper presents a novel network for shadow detection by analyzing image context in a direction-aware manner and achieves 97% accuracy and 38% reduction on balance error rate. Expand
  • 75
  • 17
  • PDF
Recurrently Aggregating Deep Features for Salient Object Detection
TLDR
We propose a novel deep saliency network equipped with recurrently aggregated deep features (RADF) to more accurately detect salient objects from an image by fully exploiting the complementary saliency information captured in different layers. Expand
  • 58
  • 13
Depth-Attentional Features for Single-Image Rain Removal
TLDR
We design an end-to-end deep neural network, where we train it to learn depth-attentional features via a depth-guided attention mechanism and regress a residual map to produce the rain-free image output. Expand
  • 51
  • 13
  • PDF
Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection
TLDR
This paper presents a network to detect shadows by exploring and combining global context in deep layers and local context in shallow layers of a deep convolutional neural network (CNN). Expand
  • 47
  • 12
  • PDF
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
TLDR
We present a novel uncertainty-aware semi-supervised framework for left atrium segmentation from 3D MR images by additionally leveraging the unlabeled data. Expand
  • 54
  • 11
  • PDF
A handle bar metaphor for virtual object manipulation with mid-air interaction
TLDR
A novel handle bar metaphor is proposed as an effective visual control metaphor between the user's hand gestures and the corresponding virtual object manipulation operations. Expand
  • 149
  • 10
  • PDF
Joint Bi-layer Optimization for Single-Image Rain Streak Removal
TLDR
We present a novel method for removing rain streaks from a single input image by decomposing it into rain-free background layer B and a rain-streak layer R. Expand
  • 107
  • 8
  • PDF