Home 3D body scans from noisy image and range data

By Alexander Weiss, David A. Hirshberg, Michael J. Black. Vision, 2011

343 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d6ac8f9959636fa910d74402fb71e89622fe3b55

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Video Based Reconstruction of 3D People Models (2018, background): “Despite remarkable progress in reconstructing 3D body models [6, 71, 81] or free-form surface [86, 44, 47, 21] from depth data, 3D reconstruction of humans in clothing from monocular video (without a pre-recorded scan of the person) has not been addressed before.”
OpenDR: An Approximate Differentiable Renderer (2014, background): “[36] estimate both human pose and shape using range data from Kinect and an edge term corresponding to the boundary of the human body.”
User-Specific Hand Modeling from Monocular Depth Sequences (2014, background): “Having built a PCM (or having simultaneously discovered alignment and PCM [10, 6]), a wide variety of impressive applications are enabled, such as the fitting of accurate 3D body models to a small number of range scans [30], or accurate hand or body tracking [7, 9].”
Learning an efficient model of hand shape variation from depth images (2015, background): “Learning a lower dimensional parametrization of shape from examples of range scans or other 3D data has proved effective in creating generic morphable models for human bodies and faces [7, 4, 5, 13, 10, 29, 17, 27, 30, 16, 31, 19].”
3D Menagerie: Modeling the 3D Shape and Pose of Animals (2016, positive): “ kp() = X k ˆ(jjx 1 jk mj jXk m j=1 ( v k j ;) jj 2); (12) where ˆis the Geman-McClure robust error function [15]. Silhouette reprojection. We encourage silhouette coverage and consistency similar to [19, 21, 33] using a bi-directional distance: E silh() = X x2S^ D S(x) + X x2S ˆ(min ^x2S^ jjx ^xjj ”
Scanning 3D Full Human Bodies Using Kinects (2012, methodology): “Unlike [10] which uses the subspace of SCAPE presen647 TONG ET AL: SCANNING 3D FULL HUMAN BODIES USING KINECTS”
Learning to Estimate 3D Human Pose and Shape from a Single Color Image (2018, background): “The inherent ambiguity of the problem has forced the researchers to use monocular image sequences for inference [54, 3], employ multiple camera views [36, 16], or even explore alternative sensors, like Kinect [53] or IMUs [52].”
Shape Completion from a Single RGBD Image (2017, methodology): “For special types of objects with a well-de ned parametric model, such as human faces [14], [15] and bodies [16], [17], [18], template-based methods work well.”
Synthesizing Training Images for Boosting Human 3D Pose Estimation (2016, background): “In this paper, we address a particularly important and challenging instance of this task: the estimation of human 3D pose from a single (monocular) still RGB image of a human subject, which has a multitude of applications [22, 56, 54, 16].”
Free-Viewpoint Video of Human Actors Using Multiple Handheld Kinects (2013, methodology): “[45] showed an approach to fit a parametric human”
Review of statistical shape spaces for 3D data with comparative analysis for human faces (2012, methodology): “Weiss et al. [32] proposed to use the SCAPE model to compute a 3D body scan from noisy Kinect data.”
Detailed, Accurate, Human Shape Estimation from Clothed 3D Scan Sequences (2017, background): “Methods [36, 39, 40] to estimate pose and shape from a depth sensor typically combine silhouette, depth data or color terms.”
Learning to Reconstruct People in Clothing From a Single RGB Camera (2019, methodology): “Some Depthbased methods [77, 34, 79, 84, 9] exploit the temporal information by optimizing a single shape and multiple poses (jointly or sequentially).”