Metric Regression Forests for Correspondence Estimation
Explore this paper's citation graph
Summary
A new method for inferring dense data to model correspondences, focusing on the application of human pose estimation from depth images, that leads to correspondences that are considerably more accurate than state of the art, using far fewer training images.
- Type
- article
- Published
- 2015-07-01
- Cited by
- 54
- References
- 39
- OpenAlex
- https://openalex.org/W1967437522
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:2244110
Keywords
Geodesic, Artificial intelligence, Mathematics, Metric (unit), Embedding
References
- Decision Forests for Computer Vision and Medical Image Analysis
- Optimization and Filtering for Human Motion Capture
- A Further Comparison of Splitting Rules for Decision-Tree Induction
- Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images
- Efficient regression of general-activity human poses from depth images
- Articulated Body Motion Capture by Stochastic Search
- Coupled Visual and Kinematic Manifold Models for Tracking
- Shared Kernel Information Embedding for discriminative inference
- The Importance of Attribute Selection Measures in Decision Tree Induction
- Real time motion capture using a single time-of-flight camera
- A Method for Registration of 3-D Shapes
- Metric Regression Forests for Human Pose Estimation
- Real-time human pose recognition in parts from single depth images
- On the unification of line processes, outlier rejection, and robust statistics with applications in early vision
- Fast articulated motion tracking using a sums of Gaussians body model
- Outdoor human motion capture using inverse kinematics and von mises-fisher sampling
- On Estimation of a Probability Density Function and Mode
- Hough Forests for Object Detection, Tracking, and Action Recognition
- Sparse probabilistic regression for activity-independent human pose inference
- Detailed Human Shape and Pose from Images
Cited by
- Dense Human Body Correspondences Using Convolutional Networks
- Real-time climbing pose estimation using a depth sensor
- Fusion4D
- 3D Human pose estimation: A review of the literature and analysis of covariates
- Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation
- DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild
- Unite the People: Closing the Loop Between 3D and 2D Human Representations
- Detailed, Accurate, Human Shape Estimation from Clothed 3D Scan Sequences
- Outdoor Markerless Motion Capture with Sparse Handheld Video Cameras
- ClothCap
- Dynamic FAUST: Registering Human Bodies in Motion
- Robust Human Pose Tracking For Realistic Service Robot Applications
- DensePose: Dense Human Pose Estimation in the Wild
- Body-part tracking from partial-view depth data
- Human pose estimation method based on single depth image
- Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
- Neural Body Fitting: Unifying Deep Learning and Model Based Human Pose and Shape Estimation
- Detailed Human Avatars from Monocular Video
- Combining Data-Driven 2D and 3D Human Appearance Models
- Deep inertial poser
Related papers
- AN EFFECTIVE REVERSIBLE DATA HIDING METHOD BASED ON PIXEL-VALUE-ORDERING
- A data hiding scheme using the varieties of pixel-value differencing in multimedia images
- Densities of maximal embedding dimension numerical semigroups
- A counter-embedding IPVO based reversible data hiding technique
- About almost geodesic curves
- Models of Finseler Spaces With Given Geodesics
- The frobenius problem for some numerical semigroups with embedding dimension equal to three
- Pixel selection in a face image based on discriminant features for face recognition
- Pixel selection based on discriminant features with application to face recognition
- Numerical metric extraction in AdS/CFT