Pictorial Human Spaces: How Well Do Humans Perceive a 3D Articulated Pose?

By Elisabeta Marinoiu, Dragos Papava, Cristian Sminchisescu. 2013

24 citations recorded by the source corpus.

Human motion analysis in images and video is a central computer vision problem. Yet, there are no studies that reveal how humans perceive other people in images and how accurate they are. In this paper we aim to unveil some of the processing-as well as the levels of accuracy-involved in the 3D perception of people from images by assessing the human performance. Our contributions are: (1) the construction of an experimental apparatus that relates perception and measurement, in particular the visual and kinematic performance with respect to 3D ground truth when the human subject is presented an image of a person in a given pose, (2) the creation of a dataset containing images, articulated 2D and 3D pose ground truth, as well as synchronized eye movement recordings of human subjects, shown a variety of human body configurations, both easy and difficult, as well as their 're-enacted' 3D poses, (3) quantitative analysis revealing the human performance in 3D pose re-enactment tasks, the degree of stability in the visual fixation patterns of human subjects, and the way it correlates with different poses. We also discuss the implications of our findings for the construction of visual human sensing systems.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “Many other MoCap datasets were also released, including the Pictorial Human Spaces [93], CMU Multi-”
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments (2014, background): “This methodolgy is pursued in our recent work [56], and we refer the interested reader to it for details.”
Action from Still Image Dataset and Inverse Optimal Control to Learn Task Specific Visual Scanpaths (2013, background): “Human gaze pattern annotations have been collected for both static images[11, 13, 14, 12, 26, 18] and for video[19, 23, 15], see [24] for a recent overview.”
3D Human pose estimation: A review of the literature and analysis of covariates (2016, background): “[57] investigated how humans perceive the pictorial 3D pose space, and how this perception can be connected with the regular 3D space we move in.”
On Self-Contact and Human Pose (2021, background): “[29] motion capture subjects reenacting a 3D pose from a 2D image.”