Search Results for author:
Found 47 papers, 16 papers with code
Mirror-Aware Neural Humans
Human motion capture either requires multi-camera systems or is unreliable using single-view input due to depth ambiguities.
Pose Modulated Avatars from Video
It is now possible to reconstruct dynamic human motion and shape from a sparse set of cameras using Neural Radiance Fields (NeRF) driven by an underlying skeleton.
NPC: Neural Point Characters from Video
Previous methods avoid using a template but rely on a costly or ill-posed mapping from observation to canonical space.
Few-shot Geometry-Aware Keypoint Localization
Supervised keypoint localization methods rely on large manually labeled image datasets, where objects can deform, articulate, or occlude.
Scaling Neural Face Synthesis to High FPS and Low Latency by Neural Caching
The warping with a shallow network reduces latency and the caching operations can further be parallelized to improve the frame rate.
UNeRF: Time and Memory Conscious U-Shaped Network for Training Neural Radiance Fields
Neural Radiance Fields (NeRFs) increase reconstruction detail for novel view synthesis and scene reconstruction, with applications ranging from large static scenes to dynamic human motion.
AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints
Our key ingredients are i) an encoder that predicts keypoint locations in an input image, ii) a shared graph as a latent variable that links the same pairs of keypoints in every image, iii) an intermediate edge map that combines the latent graph edge weights and keypoint locations in a soft, differentiable manner, and iv) an inpainting objective on randomly masked images.
Ranked #1 on
Unsupervised Landmark Detection
on MAFL Unaligned
LatentKeypointGAN: Controlling Images via Latent Keypoints -- Extended Abstract
Generative adversarial networks (GANs) can now generate photo-realistic images.
DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks
While a few such approaches exist, those have limited generalization capabilities and are prone to learning spurious (chance) correlations between irrelevant body parts, resulting in implausible deformations and missing body parts on unseen poses.
A Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset
While the quality of this pseudo-ground-truth is challenging to assess due to the lack of actual ground-truth SMPL, with the Human 3. 6m dataset, we qualitatively show that our joint locations are more accurate and that our regressor leads to improved pose estimations results on the test set without any need for retraining.
Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment
To that end, we propose to learn exercise-oriented image and video representations from unlabeled samples such that a small dataset annotated by experts suffices for supervised error detection.
Improved 2D Keypoint Detection in Out-of-Balance and Fall Situations -- combining input rotations and a kinematic model
Injury analysis may be one of the most beneficial applications of deep learning based human pose estimation.
AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation
To this end, we propose AdaptPose, an end-to-end framework that generates synthetic 3D human motions from a source dataset and uses them to fine-tune a 3D pose estimator.
ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses
Human pose estimation from single images is a challenging problem that is typically solved by supervised learning.
Ranked #1 on
Unsupervised 3D Human Pose Estimation
on Human3.6M
3D Human Pose Estimation
Unsupervised 3D Human Pose Estimation
+1
GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation
Segmenting an image into its parts is a frequent preprocess for high-level vision tasks such as image editing.
Ranked #2 on
Unsupervised Human Pose Estimation
on DeepFashion
NRST: Non-rigid Surface Tracking from Monocular Video
Our texture term exploits the orientation information in the micro-structures of the objects, e. g., the yarn patterns of fabrics.
TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation from Video
Estimating 3D human poses from video is a challenging problem.
Ranked #11 on
Weakly-supervised 3D Human Pose Estimation
on Human3.6M
LatentKeypointGAN: Controlling GANs via Latent Keypoints
Generative adversarial networks (GANs) have attained photo-realistic quality in image generation.
Ranked #4 on
Unsupervised Human Pose Estimation
on DeepFashion
A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose
We propose a method to learn a generative neural body model from unlabelled monocular videos by extending Neural Radiance Fields (NeRFs).
AudioViewer: Learning to Visualize Sounds
Different from existing models that translate to hand sign language, between speech and text, or text and images, we target immediate and low-level audio to video translation that applies to generic environment sounds as well as human speech.
Human Detection and Segmentation via Multi-view Consensus
Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data.
Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation
In this paper we propose an unsupervised feature extraction method to capture temporal information on monocular videos, where we detect and encode subject of interest in each frame and leverage contrastive self-supervised (CSS) learning to extract rich latent vectors.
CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild
Human pose estimation from single images is a challenging problem in computer vision that requires large amounts of labeled training data to be solved accurately.
Ranked #3 on
3D Human Pose Estimation
on SkiPose
Monocular 3D Human Pose Estimation
Weakly-supervised 3D Human Pose Estimation
PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers
Our conclusion is that it is important to utilize camera calibration information when available, for classical and deep-learning-based computer vision alike.
Self-supervised Segmentation via Background Inpainting
While supervised object detection and segmentation methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on.
Ellipse Detection and Localization with Applications to Knots in Sawn Lumber Images
Specific to the lumber application, we also propose an algorithm to correct any misalignment in the raw timber images during scanning, and contribute the first open-source lumber knot dataset by labeling the elliptical knots in the preprocessed images.
Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals
We compare our approach with existing domain transfer methods and demonstrate improved pose estimation accuracy on Drosophila melanogaster (fruit fly), Caenorhabditis elegans (worm) and Danio rerio (zebrafish), without requiring any manual annotation on the target domain and despite using simplistic off-the-shelf animal characters for simulation, or simple geometric shapes as models.
Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction
Reconstruction of a 3D shape from a single 2D image is a classical computer vision problem, whose difficulty stems from the inherent ambiguity of recovering occluded or only partially observed surfaces.
ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture
The accuracy of monocular 3D human pose estimation depends on the viewpoint from which the image is captured.
Gravity as a Reference for Estimating a Person's Height from Video
We show theoretically and empirically that a simple motion trajectory analysis suffices to translate from pixel measurements to the person's metric height, reaching a MAE of up to 3. 9 cm on jumping motions, and that this works without camera and ground plane calibration.
Motion Capture from Pan-Tilt Cameras with Unknown Orientation
We propose a method for estimating an athlete's global 3D position and articulated pose using multiple cameras.
Self-supervised Training of Proposal-based Segmentation via Background Prediction
While supervised object detection methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on.
XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera
The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals. We contribute a new architecture for this CNN, called SelecSLS Net, that uses novel selective long and short range skip connections to improve the information flow allowing for a drastically faster network without compromising accuracy.
Ranked #6 on
3D Multi-Person Pose Estimation
on MuPoTS-3D
3D Multi-Person Human Pose Estimation
3D Multi-Person Pose Estimation
+1
Neural Scene Decomposition for Multi-Person Motion Capture
To this end, we introduce a self-supervised approach to learning what we call a neural scene decomposition (NSD) that can be exploited for 3D pose estimation.
What Face and Body Shapes Can Tell About Height
Recovering a person's height from a single image is important for virtual garment fitting, autonomous driving and surveillance, however, it is also very challenging due to the absence of absolute scale information.
Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation
In this paper, we propose to overcome this problem by learning a geometry-aware body representation from multi-view images without annotations.
Ranked #27 on
Weakly-supervised 3D Human Pose Estimation
on Human3.6M
Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera
We tackle these challenges based on a novel lightweight setup that converts a standard baseball cap to a device for high-quality pose estimation based on a single cap-mounted fisheye camera.
Learning Monocular 3D Human Pose Estimation from Multi-view Images
Accurate 3D human pose estimation from single images is possible with sophisticated deep-net architectures that have been trained on very large datasets.
MonoPerfCap: Human Performance Capture from Monocular Video
Reconstruction from monocular video alone is drastically more challenging, since strong occlusions and the inherent depth ambiguity lead to a highly ill-posed reconstruction problem.
VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
A real-time kinematic skeleton fitting method uses the CNN output to yield temporally stable 3D global pose reconstructions on the basis of a coherent kinematic skeleton.
Ranked #16 on
Pose Estimation
on Leeds Sports Poses
EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras (Extended Abstract)
Marker-based and marker-less optical skeletal motion-capture methods use an outside-in arrangement of cameras placed around a scene, with viewpoints converging on the center.
Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
We propose a CNN-based approach for 3D human body pose estimation from single RGB images that addresses the issue of limited generalizability of models trained solely on the starkly limited publicly available 3D pose data.
Ranked #17 on
Pose Estimation
on Leeds Sports Poses
Model-based Outdoor Performance Capture
We propose a new model-based method to accurately reconstruct human performances captured outdoors in a multi-camera setup.
EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras
We therefore propose a new method for real-time, marker-less and egocentric motion capture which estimates the full-body skeleton pose from a lightweight stereo pair of fisheye cameras that are attached to a helmet or virtual reality headset.
General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues
Our method uses a new image formation model with analytic visibility and analytically differentiable alignment energy.
Real-Time Hand Tracking Using a Sum of Anisotropic Gaussians Model
In this paper, we propose a new approach that tracks the full skeleton motion of the hand from multiple RGB cameras in real-time.
A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation
Generative reconstruction methods compute the 3D configuration (such as pose and/or geometry) of a shape by optimizing the overlap of the projected 3D shape model with images.
