• Publications
  • Influence
Accurate Image Super-Resolution Using Very Deep Convolutional Networks
TLDR
We present a highly accurate single-image superresolution (SR) method based on a very deep convolutional network inspired by VGG-net. Expand
  • 2,821
  • 719
  • PDF
Enhanced Deep Residual Networks for Single Image Super-Resolution
TLDR
In this paper, we develop an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods. Expand
  • 1,835
  • 486
  • PDF
Deeply-Recursive Convolutional Network for Image Super-Resolution
TLDR
We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Expand
  • 1,235
  • 188
  • PDF
Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
TLDR
We propose a multi-scale convolutional neural network that restores sharp images in an end-to-end manner where blur is caused by various sources. Expand
  • 633
  • 175
  • PDF
Visual tracking decomposition
TLDR
We propose a novel tracking algorithm that can work robustly in a challenging scenario such that several kinds of appearance and motion changes of an object occur at the same time. Expand
  • 1,212
  • 171
  • PDF
Reweighted Random Walks for Graph Matching
TLDR
In this paper, we introduce a random walk view on the problem and propose a robust graph matching algorithm against outliers and deformation. Expand
  • 373
  • 109
  • PDF
NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results
TLDR
This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results. Expand
  • 595
  • 59
  • PDF
Tracking by Sampling Trackers
TLDR
We propose a novel tracking framework called visual tracker sampler that tracks a target robustly in the real-world tracking environments and outperforms the state-of-the-art tracking methods. Expand
  • 417
  • 51
  • PDF
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map
TLDR
We propose the V2V-PoseNet, a voxel-to-voxel prediction network for 3D hand and human pose estimation from a single depth map that performs perspective distortion-invariant estimation. Expand
  • 173
  • 48
  • PDF
Hyper-graph matching via reweighted random walks
TLDR
We generalize the previous hyper-graph matching formulations to cover relations of features in arbitrary orders, and propose a novel state-of-the-art algorithm by reinterpreting the random walk concept on the hypergraph in a probabilistic manner. Expand
  • 156
  • 26
  • PDF
...
1
2
3
4
5
...