Due to the DNS switch, the system will be going down. Please save your work and logout.
Search
Now showing items 1-2 of 2
3D Human Shape and Pose from a Single Depth Image with Deep Dense Correspondence Enabled Model Fitting
(The Eurographics Association, 2022)
We propose a two-stage hybrid method, with no initialization, for 3D human shape and pose estimation from a single depth image, combining the benefits of deep learning and optimization. First, a convolutional neural network ...
Fast and Fine Disparity Reconstruction for Wide-baseline Camera Arrays with Deep Neural Networks
(The Eurographics Association, 2022)
Recently, disparity-based 3D reconstruction for stereo camera pairs and light field cameras have been greatly improved with the uprising of deep learning-based methods. However, only few of these approaches address ...