Metric Regression Forests for Correspondence Estimation

By Gerard Pons-Moll, Jonathan Taylor, Jamie Shotton, Aaron Hertzmann, Andrew William Fitzgibbon. 2015

54 citations recorded by the source corpus.

Subfields: Computational Mechanics, 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 Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

DensePose: Dense Human Pose Estimation in the Wild (2018, background): “The task of establishing dense correspondences from an image to a surface-based model has been addressed mostly in the setting where a depth sensor is available [43, 34, 46].”
Dense Human Body Correspondences Using Convolutional Networks (2015, background): “Regression forests [41, 31] can also be used to infer geometric locations from depth image, however such methods has not yet achieve comparable accuracies with state-of-the-art registration method on full or partial data [10].”
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation (2016, unknown): “Discriminative methods aim at predicting 3D pose directly from the input data, may it be single images [28, 29, 37, 38, 39, 46, 52, 55, 64, 74], depth images [23, 50, 59], or short image sequences [65].”
Unite the People: Closing the Loop Between 3D and 2D Human Representations (2017, background): “Body representations beyond 3D skeletons have a long history in the computer vision community [17, 30, 31, 35].”
Detailed, Accurate, Human Shape Estimation from Clothed 3D Scan Sequences (2017, background): “In [33] they estimate the pose and shape from depth data combining bottom up correspondences with top down model fitting.”
Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image (2016, methodology): “While previous work uses approximations to detect interpenetrations [38,46], we believe this regression from shape parameters is novel.”
Dynamic FAUST: Registering Human Bodies in Motion (2017, background): “One option is to generate synthetic data to learn the correspondences to a common template [40, 51] but that is not as rich as real data.”
ClothCap (2017, methodology): “Our method requires as input a point cloud with texture, here we used the same active stereo system as in (Pons-Moll et al. 2015a).”
Fusing 2D Uncertainty and 3D Cues for Monocular Body Pose Estimation (2016, unknown): “Discriminative methods aim at predicting 3D pose directly from the input data, may it be single images [26, 27, 34, 35, 36, 46, 49, 58, 67], depth images [22, 44, 52], or short image sequences [59].”
Neural Body Fitting: Unifying Deep Learning and Model Based Human Pose and Shape Estimation (2018, methodology): “Some works regress correspondences to a body model which are then used to fit the model to depth data [43, 58].”
Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning (2018, methodology): “Other techniques use inferred 2D keypoint detectors and learned 3D priors to perform “2D-to-3D-lifting” [41, 7, 66, 33] or find data-to-model correspondences from depth images [40].”
DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild (2016, background): “ndence [31,4] have shown the merit of CNN-based unary terms for correspondence. There are works that address the problem of establishing dense correspondence for the human body from static RGBD images[43,37,49]. In our case we tackle the much more challenging task of establishing a 2D to 3D correspo”
DoubleFusion: Real-Time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor (2018, methodology): “Some approaches [37, 32] use a random forest to predict correspondences to a template, and use them to fit the template to the depth data.”