Published on Fri Oct 12 2018

4D Human Body Correspondences from Panoramic Depth Maps

Zhong Li, Minye Wu, Wangyiteng Zhou, Jingyi Yu

The availability of affordable 3D full body reconstruction systems has given rise to free-viewpoint video (FVV) of human shapes. Most existing solutions produce temporally uncorrelated point clouds or meshes with unknown point/vertex correspondences.

0
0
0
Abstract

The availability of affordable 3D full body reconstruction systems has given rise to free-viewpoint video (FVV) of human shapes. Most existing solutions produce temporally uncorrelated point clouds or meshes with unknown point/vertex correspondences. Individually compressing each frame is ineffective and still yields to ultra-large data sizes. We present an end-to-end deep learning scheme to establish dense shape correspondences and subsequently compress the data. Our approach uses sparse set of "panoramic" depth maps or PDMs, each emulating an inward-viewing concentric mosaics. We then develop a learning-based technique to learn pixel-wise feature descriptors on PDMs. The results are fed into an autoencoder-based network for compression. Comprehensive experiments demonstrate our solution is robust and effective on both public and our newly captured datasets.

Tue Jun 22 2021
Computer Vision
Deep3DPose: Realtime Reconstruction of Arbitrarily Posed Human Bodies from Single RGB Images
We introduce an approach that accurately reconstructs 3D human poses andDetailed 3D full-body geometric models from single images in realtime. We show that the realtime reconstruction reaches in accurate fitting that has not been seen before, especially for wild images.
0
0
0
Sat Jun 06 2020
Computer Vision
UCLID-Net: Single View Reconstruction in Object Space
Most state-of-the-art deep geometric learning single-view reconstruction approaches rely on encoder-decoder architectures that output either shape parametrizations or implicit representations. However, these representations rarely preserve the Euclidean structure of the 3D space objects exist in. We
0
0
0
Tue Dec 10 2019
Computer Vision
3D-GMNet: Single-View 3D Shape Recovery as A Gaussian Mixture
3D-GMNet is a deep neural network for 3D object shape reconstruction from a single image. As the name suggests, it covers 3D shape as a Gaussian mixture. It offers a number of additional advantages including instant pose estimation and controllable level of detail reconstruction.
0
0
0
Wed Apr 01 2020
Computer Vision
Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation
0
0
0
Tue Nov 17 2020
Computer Vision
A Divide et Impera Approach for 3D Shape Reconstruction from Multiple Views
This paper proposes to rely on viewpoint variant reconstructions by merging the visible information from the given views. We first align them into a common coordinate system by estimating the relative pose between all the pairs. Then, inspired by the traditional voxel carving, we generate an occupancy grid of
0
0
0
Thu Jul 20 2017
Computer Vision
3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks
A method for reconstructing 3D shapes from 2D sketches in the form of line drawings. The method takes as input a single sketch and outputs a dense point cloud representing a 3D reconstruction of the input sketch. The point cloud is then converted into a polygon mesh.
0
0
0