• Publications
  • Influence
SurfaceNet: An End-to-End 3D Neural Network for Multiview Stereopsis
TLDR
The key advantage of the framework is that both photo-consistency as well geometric relations of the surface structure can be directly learned for the purpose of multiview stereopsis in an end-to-end fashion. Expand
CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping
TLDR
Using cross-scale warping, the CrossNet network is able to perform spatial alignment at pixel-level in an end-to-end fashion, which improves the existing schemes both in precision and efficiency. Expand
Learning High-level Prior with Convolutional Neural Networks for Semantic Segmentation
TLDR
A convolutional neural network that can fuse high-level prior for semantic image segmentation and a generative model called conditional variational auto-encoder (CVAE) that can build up the links behind these three layers. Expand
Deep Learning for Surface Material Classification Using Haptic and Visual Information
TLDR
A novel deep learning method dealing with the surface material classification problem based on a fully convolutional network, which takes the aforementioned acceleration signal and a corresponding image of the surface texture as inputs and automatically extracts discriminative features utilizing advanced deeplearning methodologies. Expand
Preprocessing-free surface material classification using convolutional neural networks pretrained by sparse Autoencoder
TLDR
This work uses a trained sparse Autoencoder to initialize the weights of the first convolution layers of the CNN, named CNN pretrained by sparse AE (ACNN), and shows that the proposed algorithm performs favorably against existing methods. Expand
Local stereo matching with adaptive shape support window based cost aggregation.
TLDR
A novel local stereo-matching algorithm with a cost-aggregation method based on adaptive shape support window (ASSW) that achieves outstanding matching performance compared with other existing local algorithms on the Middlebury stereo benchmark, especially in depth discontinuities and piecewise smooth regions. Expand
Learning Cross-scale Correspondence and Patch-based Synthesis for Reference-based Super-Resolution
TLDR
Experiments on MPI Sintel Dataset and Light-Field video dataset demonstrate the learned correspondence features outperform existing features, and the proposed RefSR-Net substantially outperforms conventional single image SR and exemplar-based SR approaches. Expand
RegNet: Learning the Optimization of Direct Image-to-Image Pose Registration
TLDR
It is demonstrated that the inaccurate numerical Jacobian limits the convergence range which could be improved greatly using learned approaches, and a novel end-to-end network is proposed, RegNet, to learn the optimization of image- to-image pose registration. Expand
Augmenting vascular disease diagnosis by vasculature-aware unsupervised learning
TLDR
The authors present VasNet, a vasculature-aware unsupervised learning algorithm that augments pathovascular recognition from small sets of unlabelled fluorescence and digital subtraction angiography images that demonstrates the utility of their diagnostic approach on vascular images of thrombosis, internal bleeding and colitis. Expand
A comprehensive study on digital image matting
TLDR
A unified framework for digital image matting is introduced, which provides the possibility of obtaining a better understanding and direction of further improvement for image matts problem and proves the feasibility of the proposed framework. Expand
...
1
2
...