7 accepted papers
We address the 3D head reconstruction problem and the facial correspondence search problem in a unified framework, named as WarpHE4D. The underlying idea is to establish correspondences between the facial image and the fixed UV texture map by exploiting powerful self-supervised visual representation…
"We present a novel framework for reconstructing animatable human avatars from multiple images, termed CanonicalFusion. Our central concept involves integrating individual reconstruction results into the canonical space. To be specific, we first predict Linear Blend Skinning (LBS) weight maps and de…
High-quality 3D human body reconstruction requires high-fidelity and large-scale training data and appropriate network design that effectively exploits the high-resolution input images. To tackle these problems, we propose a simple yet effective 3D human digitization method called 2K2K, which constr…
We introduce a new method to find a salient viewpoint with a deep representation, according to ease of semantic segmentation. The main idea in our segmentation network is to utilize the multipath network with informative two views. In order to collect training samples, we assume all the information
Recent advances in deep learning have significantly improved the performance of video prediction, however, top-performing algorithms start to generate blurry predictions as they attempt to predict farther future frames. In this paper, we propose a unified generative adversarial network for predictin…
In this paper, we propose an approach to jointly solve scene layout estimation and global registration problems for accurate indoor 3D reconstruction. Given a sequence of range data, we build a set of scene fragments using KinectFusion and register them through pose graph optimization. Afterwards, w…
We propose a new approach to associate supervised learning-based confidence prediction with the stereo matching problem. First of all, we analyze the characteristics of various confidence measures in the regression forest framework to select effective confidence measures using training data. We then…