The Experts below are selected from a list of 360 Experts worldwide ranked by ideXlab platform
Kyoung Mu Lee - One of the best experts on this subject based on the ideXlab platform.
-
neuralannot neural annotator for in the wild expressive 3d human pose and mesh training sets
arXiv: Computer Vision and Pattern Recognition, 2020Co-Authors: Gyeongsik Moon, Kyoung Mu LeeAbstract:Recovering expressive 3D human pose and mesh from in-the-wild images is greatly challenging due to the absence of the training data. Several optimization-based methods have been used to obtain 3D human model fits from GT 2D poses, which serve as pseudo-groundtruth (GT) 3D poses and meshes. However, they often suffer from severe depth ambiguity while requiring long running time because of their per-sample optimization that only uses 2D supervisions and priors. The per-sample optimization optimizes a 3D human model on each sample independently; therefore, running it on a large number of samples consumes long running time. In addition, the absence of the 3D supervisions makes their framework suffer from depth ambiguity. To overcome the limitations, we present NeuralAnnot, a neural annotator that learns to construct in-the-wild expressive 3D human pose and mesh training sets. Our NeuralAnnot is trained on entire datasets by considering multiple samples together with additional 3D supervisions from auxiliary datasets; therefore, it produces far better 3D pseudo-GT fits much faster. We show that the newly obtained training set brings great performance gain, which will be publicly released with codes.
-
DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling
2020Co-Authors: Moon Gyeongsik, Shiratori Takaaki, Kyoung Mu LeeAbstract:Human hands play a central role in interacting with other people and objects. For realistic replication of such hand motions, high-fidelity hand meshes have to be reconstructed. In this study, we firstly propose DeepHandMesh, a weakly-supervised deep encoder-decoder framework for high-fidelity hand mesh modeling. We design our system to be trained in an end-to-end and weakly-supervised manner; therefore, it does not require groundtruth meshes. Instead, it relies on weaker supervisions such as 3D joint coordinates and multi-view depth maps, which are easier to get than groundtruth meshes and do not dependent on the mesh topology. Although the proposed DeepHandMesh is trained in a weakly-supervised way, it provides significantly more realistic hand mesh than previous fully-supervised hand models. Our newly introduced penetration avoidance loss further improves results by replicating physical interaction between hand parts. Finally, we demonstrate that our system can also be applied successfully to the 3D hand mesh estimation from general images. Our hand model, dataset, and codes are publicly available at https://mks0601.github.io/DeepHandMesh/.Comment: Published at ECCV 2020 (Oral
-
camera distance aware top down approach for 3d multi person pose estimation from a single rgb image
International Conference on Computer Vision, 2019Co-Authors: Gyeongsik Moon, Ju Yong Chang, Kyoung Mu LeeAbstract:Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly propose a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. The pipeline of the proposed system consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. Our system achieves comparable results with the state-of-the-art 3D single-person pose estimation models without any groundtruth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in \footnote{\url{https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE}}\textsuperscript{,}\footnote{\url{https://github.com/mks0601/3DMPPE_POSENET_RELEASE}}.
-
camera distance aware top down approach for 3d multi person pose estimation from a single rgb image
arXiv: Computer Vision and Pattern Recognition, 2019Co-Authors: Gyeongsik Moon, Ju Yong Chang, Kyoung Mu LeeAbstract:Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly propose a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. The pipeline of the proposed system consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. Our system achieves comparable results with the state-of-the-art 3D single-person pose estimation models without any groundtruth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in this https URL , this https URL.
-
Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image
2019Co-Authors: Moon Gyeongsik, Chang, Ju Yong, Kyoung Mu LeeAbstract:Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly propose a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. The pipeline of the proposed system consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. Our system achieves comparable results with the state-of-the-art 3D single-person pose estimation models without any groundtruth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE , https://github.com/mks0601/3DMPPE_POSENET_RELEASE.Comment: Published at ICCV 201
Gyeongsik Moon - One of the best experts on this subject based on the ideXlab platform.
-
neuralannot neural annotator for in the wild expressive 3d human pose and mesh training sets
arXiv: Computer Vision and Pattern Recognition, 2020Co-Authors: Gyeongsik Moon, Kyoung Mu LeeAbstract:Recovering expressive 3D human pose and mesh from in-the-wild images is greatly challenging due to the absence of the training data. Several optimization-based methods have been used to obtain 3D human model fits from GT 2D poses, which serve as pseudo-groundtruth (GT) 3D poses and meshes. However, they often suffer from severe depth ambiguity while requiring long running time because of their per-sample optimization that only uses 2D supervisions and priors. The per-sample optimization optimizes a 3D human model on each sample independently; therefore, running it on a large number of samples consumes long running time. In addition, the absence of the 3D supervisions makes their framework suffer from depth ambiguity. To overcome the limitations, we present NeuralAnnot, a neural annotator that learns to construct in-the-wild expressive 3D human pose and mesh training sets. Our NeuralAnnot is trained on entire datasets by considering multiple samples together with additional 3D supervisions from auxiliary datasets; therefore, it produces far better 3D pseudo-GT fits much faster. We show that the newly obtained training set brings great performance gain, which will be publicly released with codes.
-
camera distance aware top down approach for 3d multi person pose estimation from a single rgb image
International Conference on Computer Vision, 2019Co-Authors: Gyeongsik Moon, Ju Yong Chang, Kyoung Mu LeeAbstract:Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly propose a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. The pipeline of the proposed system consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. Our system achieves comparable results with the state-of-the-art 3D single-person pose estimation models without any groundtruth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in \footnote{\url{https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE}}\textsuperscript{,}\footnote{\url{https://github.com/mks0601/3DMPPE_POSENET_RELEASE}}.
-
camera distance aware top down approach for 3d multi person pose estimation from a single rgb image
arXiv: Computer Vision and Pattern Recognition, 2019Co-Authors: Gyeongsik Moon, Ju Yong Chang, Kyoung Mu LeeAbstract:Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly propose a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. The pipeline of the proposed system consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. Our system achieves comparable results with the state-of-the-art 3D single-person pose estimation models without any groundtruth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in this https URL , this https URL.
Timothy D Barfoot - One of the best experts on this subject based on the ideXlab platform.
-
variational inference with parameter learning applied to vehicle trajectory estimation
International Conference on Robotics and Automation, 2020Co-Authors: Jeremy N Wong, David J Yoon, Angela P Schoellig, Timothy D BarfootAbstract:We present parameter learning in a Gaussian variational inference setting using only noisy measurements (i.e., no groundtruth). This is demonstrated in the context of vehicle trajectory estimation, although the method we propose is general. The letter extends the Exactly Sparse Gaussian Variational Inference (ESGVI) framework, which has previously been used for large-scale nonlinear batch state estimation. Our contribution is to additionally learn parameters of our system models (which may be difficult to choose in practice) within the ESGVI framework. In this letter, we learn the covariances for the motion and sensor models used within vehicle trajectory estimation. Specifically, we learn the parameters of a white-noise-on-acceleration motion model and the parameters of an Inverse-Wishart prior over measurement covariances for our sensor model. We demonstrate our technique using a 36 km dataset consisting of a car using lidar to localize against a high-definition map; we learn the parameters on a training section of the data and then show that we achieve high-quality state estimates on a test section, even in the presence of outliers. Lastly, we show that our framework can be used to solve pose graph optimization even with many false loop closures.
-
variational inference with parameter learning applied to vehicle trajectory estimation
arXiv: Robotics, 2020Co-Authors: Jeremy N Wong, David J Yoon, Angela P Schoellig, Timothy D BarfootAbstract:We present parameter learning in a Gaussian variational inference setting using only noisy measurements (i.e., no groundtruth). This is demonstrated in the context of vehicle trajectory estimation, although the method we propose is general. The paper extends the Exactly Sparse Gaussian Variational Inference (ESGVI) framework, which has previously been used for large-scale nonlinear batch state estimation. Our contribution is to additionally learn parameters of our system models (which may be difficult to choose in practice) within the ESGVI framework. In this paper, we learn the covariances for the motion and sensor models used within vehicle trajectory estimation. Specifically, we learn the parameters of a white-noise-on-acceleration motion model and the parameters of an Inverse-Wishart prior over measurement covariances for our sensor model. We demonstrate our technique using a 36~km dataset consisting of a car using lidar to localize against a high-definition map; we learn the parameters on a training section of the data and then show that we achieve high-quality state estimates on a test section, even in the presence of outliers. Lastly, we show that our framework can be used to solve pose graph optimization even with many false loop closures.
-
decentralized cooperative slam for sparsely communicating robot networks a centralized equivalent approach
Journal of Intelligent and Robotic Systems, 2012Co-Authors: Keith Yk Leung, Timothy D BarfootAbstract:Communication between robots is key to performance in cooperative multi-robot systems. In practice, communication connections for information exchange between all robots are not always guaranteed, which adds difficulty in performing state estimation. This paper examines the decentralized cooperative simultaneous localization and mapping (SLAM) problem, in which each robot is required to estimate the map and all robot states under a sparsely-communicating and dynamic network. We show how the exact, centralized-equivalent estimate can be obtained by all robots in the network in a decentralized manner even when the network is never fully connected. Furthermore, a robot only needs to consider its own knowledge of the network topology in order to detect when the centralized-equivalent estimate is obtainable. Our approach is validated through more than 250 min of hardware experiments using a team of real robots. The resulting estimates are compared against accurate groundtruth data for all robot poses and landmark positions. In addition, we examined the effects of communication range limit on our algorithm's performance.
-
the utias multi robot cooperative localization and mapping dataset
The International Journal of Robotics Research, 2011Co-Authors: Keith Yk Leung, Yoni Halpern, Timothy D Barfoot, Hugh Ht LiuAbstract:This paper presents a two-dimensional multi-robot cooperative localization and mapping dataset collection for research and educational purposes. The dataset consists of nine sub-datasets, which can be used for studying problems such as robot-only cooperative localization, cooperative localization with a known map, and cooperative simultaneous localization and mapping (SLAM) . The data collection process is discussed in detail, including the equipment we used, how measurements were made and logged, and how we obtained groundtruth data for all robots and landmarks. The format of each file in each sub-dataset is also provided. The dataset is available for download at http://asrl.utias.utoronto.ca/datasets/mrclam/.
Alessio Del Bue - One of the best experts on this subject based on the ideXlab platform.
-
single image human proxemics estimation for visual social distancing
Proceedings of the IEEE CVF Winter Conference on Applications of Computer Vision, 2020Co-Authors: Maya Aghaei, Matteo Bustreo, Yiming Wang, Gianluca Bailo, Pietro Morerio, Alessio Del BueAbstract:In this work, we address the problem of estimating the so-called "Social Distancing" given a single uncalibrated image in unconstrained scenarios. Our approach proposes a semi-automatic solution to approximate the homography matrix between the scene ground and image plane. With the estimated homography, we then leverage an off-the-shelf pose detector to detect body poses on the image and to reason upon their inter-personal distances using the length of their body-parts. Inter-personal distances are further locally inspected to detect possible violations of the social distancing rules. We validate our proposed method quantitatively and qualitatively against baselines on public domain datasets for which we provided groundtruth on inter-personal distances. Besides, we demonstrate the application of our method deployed in a real testing scenario where statistics on the inter-personal distances are currently used to improve the safety in a critical environment.
Ju Yong Chang - One of the best experts on this subject based on the ideXlab platform.
-
camera distance aware top down approach for 3d multi person pose estimation from a single rgb image
International Conference on Computer Vision, 2019Co-Authors: Gyeongsik Moon, Ju Yong Chang, Kyoung Mu LeeAbstract:Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly propose a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. The pipeline of the proposed system consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. Our system achieves comparable results with the state-of-the-art 3D single-person pose estimation models without any groundtruth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in \footnote{\url{https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE}}\textsuperscript{,}\footnote{\url{https://github.com/mks0601/3DMPPE_POSENET_RELEASE}}.
-
camera distance aware top down approach for 3d multi person pose estimation from a single rgb image
arXiv: Computer Vision and Pattern Recognition, 2019Co-Authors: Gyeongsik Moon, Ju Yong Chang, Kyoung Mu LeeAbstract:Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly propose a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. The pipeline of the proposed system consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. Our system achieves comparable results with the state-of-the-art 3D single-person pose estimation models without any groundtruth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in this https URL , this https URL.
