Inferring 3D structure with a statistical image-based shape model

By Kristen Grauman, Gregory Shakhnarovich, Trevor Darrell. 2003

253 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Environmental Engineering, Geology

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

In Environmental Engineering

In Geology

Citations in the corpus

Lifting Object Detection Datasets into 3D (2015, methodology): “After jointly estimating the camera viewpoints for all the instances in each class, we reconstruct the 3D shape of all objects using shape information borrowed from other exem-plars in the same class 4 .”
VirtualWorlds as Proxy for Multi-object Tracking Analysis (2016, background): “From early on, computer vision researchers leveraged 3D computer simulations to model articulated objects including human shape [8], face, and hand appearance [9], or even for scene interpretation and vision as inverse graphics [10, 11, 12].”
Learning Human Pose Estimation Features with Convolutional Networks (2013, background): “Examples include “shape-context” edge-based histograms from the human body [28, 1] or just silhouette features [19].”
Learning invariance through imitation (2011, methodology): “Our learning framework has some overlap with other methods mainly in two areas: dynamical models and metric learning.”
Watching Unlabeled Video Helps Learn New Human Actions from Very Few Labeled Snapshots (2013, methodology): “humanoid models in graphics software, together with mocap data, make it possible to generate synthetic images useful for training action recognition [18] and pose estimation methods [26, 12, 27].”
3D Human pose estimation: A review of the literature and analysis of covariates (2016, methodology): “In example-based approaches, a set of exemplars with their corresponding pose descriptors is stored and the final pose is estimated by interpolating the candidates obtained from a similarity search [49, 51].”
Style-based inverse kinematics (2004, methodology): “Video motion capture using models learned from motion capture data is an active area of research [Brand 1999; Grauman et al. 2003; Howe et al. 2000; Ramanan and Forsyth 2004; Rosales and Sclaroff 2002; Sidenbladh et al. 2002].”
PARE: Part Attention Regressor for 3D Human Body Estimation (2021, unknown): “Initial work predicts the 3D body using keypoints and silhouettes [1, 4, 5, 15, 46].”
Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild (2020, background): “Seminal works in this area [18,57,4] fit the”
VIBE: Video Inference for Human Body Pose and Shape Estimation (2019, unknown): “The discriminator has access to a large corpus of human motions in SMPL format. tom up” regression approaches, “top down” optimization approaches, and multi-camera settings using keypoints and silhouettes as input [1, 8, 19, 52].”
3D Pictorial Structures for Multiple Human Pose Estimation (2014, background): “silhouettes, edges) or depth observations and 3D human body poses is learned [1, 14, 16, 20, 26, 28, 30].”
Vision-based human motion analysis: An overview (2007, background): “[30] describe a distribution over both multi-view silhouettes and 3D joint locations with a mixture of probabilistic PCA.”
Learning people detection models from few training samples (2011, background): “to learn a multi-view shape model for humans [18].”
Learning scene-specific pedestrian detectors without real data (2015, methodology): “3D computer graphics models have been used for modeling human shape [16, 7], body-part gradient templates [1], full-body gradient templates [22] and hand appearance [27, 2, 28].”
HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion (2006, methodology): “A variety of statistical [1, 2, 3, 6, 12, 36, 37, 38] as well as deterministic methods [21, 41, 35] have been developed for tracking people from single [1, 2, 7, 12, 15, 20, 21, 25, 26, 27, 29, 37] as well as multiple [3, 6, 9, 36] views.”
Pose-Sensitive Embedding by Nonlinear NCA Regression (2010, methodology): “Some extract “shape-context” edge based histograms from the human body [25, 1] or just silhouette features [15].”
3D human pose from silhouettes by relevance vector regression (2004, methodology): “Like [11, 6], we used POSERto synthesize a large set of training and test images from different viewpoints, but rather than using random synthetic poses, we used poses taken from real human motion capture sequences.”