Filters








131 Hits in 1.7 sec

Ebû Yûsuf'un İbadet Konularında Ebû Hanîfe ve Muhammed eş-Şeybânî'den Farklı Görüşleri ve Nedenleri

Savaş Kocabaş
2020 Zenodo  
Ebû Yûsuf Hanefî mezhebinin ikinci kurucu imâmı olduğu gibi, mezhebin müdevvini ve üçüncü imâmı olan Muhammed eş-Şeybânî'nin de hocasıdır.  ...  Bu çalışmada Hanefî mezhebindeki en önemli üç imâmdan biri olan Ebû Yûsuf'un hayatı ve ilmi şahsiyeti, diğer iki Hanefî imâmı Ebû Hanîfe ile Muhammed b.  ...  Muhammed b.  ... 
doi:10.5281/zenodo.4399286 fatcat:63am6rnv45hqbowney7zphud2a

MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network [article]

Muhammed Kocabas, Salih Karagoz, Emre Akbas
2018 arXiv   pre-print
In this paper, we present MultiPoseNet, a novel bottom-up multi-person pose estimation architecture that combines a multi-task model with a novel assignment method. MultiPoseNet can jointly handle person detection, keypoint detection, person segmentation and pose estimation problems. The novel assignment method is implemented by the Pose Residual Network (PRN) which receives keypoint and person detections, and produces accurate poses by assigning keypoints to person instances. On the COCO
more » ... nts dataset, our pose estimation method outperforms all previous bottom-up methods both in accuracy (+4-point mAP over previous best result) and speed; it also performs on par with the best top-down methods while being at least 4x faster. Our method is the fastest real time system with 23 frames/sec. Source code is available at: https://github.com/mkocabas/pose-residual-network
arXiv:1807.04067v1 fatcat:kazintu5fjajtdq24eypr7m5dm

Articulated Objects in Free-form Hand Interaction [article]

Zicong Fan, Omid Taheri, Dimitrios Tzionas, Muhammed Kocabas, Manuel Kaufmann, Michael J. Black, Otmar Hilliges
2022 arXiv   pre-print
We use our hands to interact with and to manipulate objects. Articulated objects are especially interesting since they often require the full dexterity of human hands to manipulate them. To understand, model, and synthesize such interactions, automatic and robust methods that reconstruct hands and articulated objects in 3D from a color image are needed. Existing methods for estimating 3D hand and object pose from images focus on rigid objects. In part, because such methods rely on training data
more » ... and no dataset of articulated object manipulation exists. Consequently, we introduce ARCTIC - the first dataset of free-form interactions of hands and articulated objects. ARCTIC has 1.2M images paired with accurate 3D meshes for both hands and for objects that move and deform over time. The dataset also provides hand-object contact information. To show the value of our dataset, we perform two novel tasks on ARCTIC: (1) 3D reconstruction of two hands and an articulated object in interaction; (2) an estimation of dense hand-object relative distances, which we call interaction field estimation. For the first task, we present ArcticNet, a baseline method for the task of jointly reconstructing two hands and an articulated object from an RGB image. For interaction field estimation, we predict the relative distances from each hand vertex to the object surface, and vice versa. We introduce InterField, the first method that estimates such distances from a single RGB image. We provide qualitative and quantitative experiments for both tasks, and provide detailed analysis on the data. Code and data will be available at https://arctic.is.tue.mpg.de.
arXiv:2204.13662v1 fatcat:ch43avcbsjgupns4f7ripgqixy

SPEC: Seeing People in the Wild with an Estimated Camera [article]

Muhammed Kocabas, Chun-Hao P. Huang, Joachim Tesch, Lea Müller, Otmar Hilliges, Michael J. Black
2021 arXiv   pre-print
Due to the lack of camera parameter information for in-the-wild images, existing 3D human pose and shape (HPS) estimation methods make several simplifying assumptions: weak-perspective projection, large constant focal length, and zero camera rotation. These assumptions often do not hold and we show, quantitatively and qualitatively, that they cause errors in the reconstructed 3D shape and pose. To address this, we introduce SPEC, the first in-the-wild 3D HPS method that estimates the
more » ... camera from a single image and employs this to reconstruct 3D human bodies more accurately. %regress 3D human bodies. First, we train a neural network to estimate the field of view, camera pitch, and roll given an input image. We employ novel losses that improve the calibration accuracy over previous work. We then train a novel network that concatenates the camera calibration to the image features and uses these together to regress 3D body shape and pose. SPEC is more accurate than the prior art on the standard benchmark (3DPW) as well as two new datasets with more challenging camera views and varying focal lengths. Specifically, we create a new photorealistic synthetic dataset (SPEC-SYN) with ground truth 3D bodies and a novel in-the-wild dataset (SPEC-MTP) with calibration and high-quality reference bodies. Both qualitative and quantitative analysis confirm that knowing camera parameters during inference regresses better human bodies. Code and datasets are available for research purposes at https://spec.is.tue.mpg.de.
arXiv:2110.00620v1 fatcat:b2yinrp22jeohgthzvdicnm6g4

MultiPoseNet: Fast Multi-Person Pose Estimation Using Pose Residual Network [chapter]

Muhammed Kocabas, Salih Karagoz, Emre Akbas
2018 Lecture Notes in Computer Science  
Muhammed Kocabas [0000−0001−8593−0415] , Salih Karagoz [0000−0002−7438−8322] , and Emre Akbas [0000−0002−3760−6722] Abstract.  ... 
doi:10.1007/978-3-030-01252-6_26 fatcat:4iunbknmarbf7imstj4yupxf7m

PARE: Part Attention Regressor for 3D Human Body Estimation [article]

Muhammed Kocabas, Chun-Hao P. Huang, Otmar Hilliges, Michael J. Black
2021 arXiv   pre-print
Despite significant progress, we show that state of the art 3D human pose and shape estimation methods remain sensitive to partial occlusion and can produce dramatically wrong predictions although much of the body is observable. To address this, we introduce a soft attention mechanism, called the Part Attention REgressor (PARE), that learns to predict body-part-guided attention masks. We observe that state-of-the-art methods rely on global feature representations, making them sensitive to even
more » ... mall occlusions. In contrast, PARE's part-guided attention mechanism overcomes these issues by exploiting information about the visibility of individual body parts while leveraging information from neighboring body-parts to predict occluded parts. We show qualitatively that PARE learns sensible attention masks, and quantitative evaluation confirms that PARE achieves more accurate and robust reconstruction results than existing approaches on both occlusion-specific and standard benchmarks. The code and data are available for research purposes at
arXiv:2104.08527v2 fatcat:2yynpww6v5fufht2eefjcoalqa

HDR Syndrome Accompanying Type 1 Diabetes Mellitus and Hypopituitarism

Mustafa Can, Feridun Karakurt, Muhammed Kocabas, İlker Cordan, Melia Karakose, Mustafa Kulaksızoglu
2019 Case Reports in Endocrinology  
HDR (Hypoparathyroidism, Deafness, and Renal Dysplasia) syndrome is an autosomal dominant disorder characterized by the triad of hypoparathyroidism, sensorineural deafness, and renal disease. Approximately 65% of patients with HDR syndrome have all three of these features, while others have different combinations of these features. We aimed to present a case with primary hypoparathyroidism, hearing loss, and nondiabetic chronic kidney disease and diagnosed as HDR syndrome while being followed up for type 1 diabetes mellitus and hypopituitarism.
doi:10.1155/2019/7276947 pmid:31223507 pmcid:PMC6541993 fatcat:eerpdcig5fdnzhu4xe6gkkjqbe

Learning to Regress Bodies from Images using Differentiable Semantic Rendering [article]

Sai Kumar Dwivedi, Nikos Athanasiou, Muhammed Kocabas, Michael J. Black
2022 arXiv   pre-print
Learning to regress 3D human body shape and pose (e.g.~SMPL parameters) from monocular images typically exploits losses on 2D keypoints, silhouettes, and/or part-segmentation when 3D training data is not available. Such losses, however, are limited because 2D keypoints do not supervise body shape and segmentations of people in clothing do not match projected minimally-clothed SMPL shapes. To exploit richer image information about clothed people, we introduce higher-level semantic information
more » ... ut clothing to penalize clothed and non-clothed regions of the image differently. To do so, we train a body regressor using a novel Differentiable Semantic Rendering - DSR loss. For Minimally-Clothed regions, we define the DSR-MC loss, which encourages a tight match between a rendered SMPL body and the minimally-clothed regions of the image. For clothed regions, we define the DSR-C loss to encourage the rendered SMPL body to be inside the clothing mask. To ensure end-to-end differentiable training, we learn a semantic clothing prior for SMPL vertices from thousands of clothed human scans. We perform extensive qualitative and quantitative experiments to evaluate the role of clothing semantics on the accuracy of 3D human pose and shape estimation. We outperform all previous state-of-the-art methods on 3DPW and Human3.6M and obtain on par results on MPI-INF-3DHP. Code and trained models are available for research at https://dsr.is.tue.mpg.de/.
arXiv:2110.03480v2 fatcat:6oi25y5pw5bgdbhzunz47rh2ny

Self-Supervised Learning of 3D Human Pose using Multi-view Geometry [article]

Muhammed Kocabas and Salih Karagoz and Emre Akbas
2019 arXiv   pre-print
Training accurate 3D human pose estimators requires large amount of 3D ground-truth data which is costly to collect. Various weakly or self supervised pose estimation methods have been proposed due to lack of 3D data. Nevertheless, these methods, in addition to 2D ground-truth poses, require either additional supervision in various forms (e.g. unpaired 3D ground truth data, a small subset of labels) or the camera parameters in multiview settings. To address these problems, we present
more » ... e, a self-supervised learning method for 3D human pose estimation, which does not need any 3D ground-truth data or camera extrinsics. During training, EpipolarPose estimates 2D poses from multi-view images, and then, utilizes epipolar geometry to obtain a 3D pose and camera geometry which are subsequently used to train a 3D pose estimator. We demonstrate the effectiveness of our approach on standard benchmark datasets i.e. Human3.6M and MPI-INF-3DHP where we set the new state-of-the-art among weakly/self-supervised methods. Furthermore, we propose a new performance measure Pose Structure Score (PSS) which is a scale invariant, structure aware measure to evaluate the structural plausibility of a pose with respect to its ground truth. Code and pretrained models are available at https://github.com/mkocabas/EpipolarPose
arXiv:1903.02330v2 fatcat:uqij6bmr5bgmnemmqsoyabypq4

VIBE: Video Inference for Human Body Pose and Shape Estimation

Muhammed Kocabas, Nikos Athanasiou, Michael J. Black
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Figure 1 : Given challenging in-the-wild videos, a recent state-of-the-art video-pose-estimation approach [30] (top), fails to produce accurate 3D body poses. To address this, we exploit a large-scale motion-capture dataset to train a motion discriminator using an adversarial approach. Our model (VIBE) (bottom) is able to produce realistic and accurate pose and shape, outperforming previous work on standard benchmarks.
doi:10.1109/cvpr42600.2020.00530 dblp:conf/cvpr/KocabasAB20 fatcat:ooyp57g76vbppfl67zryxnj47a

Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry

Muhammed Kocabas, Salih Karagoz, Emre Akbas
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Training accurate 3D human pose estimators requires large amount of 3D ground-truth data which is costly to collect. Various weakly or self supervised pose estimation methods have been proposed due to lack of 3D data. Nevertheless, these methods, in addition to 2D groundtruth poses, require either additional supervision in various forms (e.g. unpaired 3D ground truth data, a small subset of labels) or the camera parameters in multiview settings. To address these problems, we present
more » ... , a self-supervised learning method for 3D human pose estimation, which does not need any 3D ground-truth data or camera extrinsics. During training, EpipolarPose estimates 2D poses from multi-view images, and then, utilizes epipolar geometry to obtain a 3D pose and camera geometry which are subsequently used to train a 3D pose estimator. We demonstrate the effectiveness of our approach on standard benchmark datasets (i.e. Human3.6M and MPI-INF-3DHP) where we set the new state-of-the-art among weakly/self-supervised methods. Furthermore, we propose a new performance measure Pose Structure Score (PSS) which is a scale invariant, structure aware measure to evaluate the structural plausibility of a pose with respect to its ground truth. Code and pretrained models are available at https://github.com/mkocabas/ EpipolarPose
doi:10.1109/cvpr.2019.00117 dblp:conf/cvpr/KocabasKA19 fatcat:c2egnq4475b2hfv27quyz6pmwe

D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions [article]

Sammy Christen, Muhammed Kocabas, Emre Aksan, Jemin Hwangbo, Jie Song, Otmar Hilliges
2022 arXiv   pre-print
Muhammed Kocabas is supported by the Max Planck ETH Center for Learning Systems.  ... 
arXiv:2112.03028v2 fatcat:fp3l5ztgubarpdzxazoxtarcee

VIBE: Video Inference for Human Body Pose and Shape Estimation [article]

Muhammed Kocabas, Nikos Athanasiou, Michael J. Black
2020 arXiv   pre-print
Human motion is fundamental to understanding behavior. Despite progress on single-image 3D pose and shape estimation, existing video-based state-of-the-art methods fail to produce accurate and natural motion sequences due to a lack of ground-truth 3D motion data for training. To address this problem, we propose Video Inference for Body Pose and Shape Estimation (VIBE), which makes use of an existing large-scale motion capture dataset (AMASS) together with unpaired, in-the-wild, 2D keypoint
more » ... ations. Our key novelty is an adversarial learning framework that leverages AMASS to discriminate between real human motions and those produced by our temporal pose and shape regression networks. We define a temporal network architecture and show that adversarial training, at the sequence level, produces kinematically plausible motion sequences without in-the-wild ground-truth 3D labels. We perform extensive experimentation to analyze the importance of motion and demonstrate the effectiveness of VIBE on challenging 3D pose estimation datasets, achieving state-of-the-art performance. Code and pretrained models are available at https://github.com/mkocabas/VIBE.
arXiv:1912.05656v3 fatcat:vrhvro6q65ftzpuzehb4ab24bu

Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation [article]

Zicong Fan, Adrian Spurr, Muhammed Kocabas, Siyu Tang, Michael J. Black, Otmar Hilliges
2021 arXiv   pre-print
In natural conversation and interaction, our hands often overlap or are in contact with each other. Due to the homogeneous appearance of hands, this makes estimating the 3D pose of interacting hands from images difficult. In this paper we demonstrate that self-similarity, and the resulting ambiguities in assigning pixel observations to the respective hands and their parts, is a major cause of the final 3D pose error. Motivated by this insight, we propose DIGIT, a novel method for estimating the
more » ... 3D poses of two interacting hands from a single monocular image. The method consists of two interwoven branches that process the input imagery into a per-pixel semantic part segmentation mask and a visual feature volume. In contrast to prior work, we do not decouple the segmentation from the pose estimation stage, but rather leverage the per-pixel probabilities directly in the downstream pose estimation task. To do so, the part probabilities are merged with the visual features and processed via fully-convolutional layers. We experimentally show that the proposed approach achieves new state-of-the-art performance on the InterHand2.6M dataset. We provide detailed ablation studies to demonstrate the efficacy of our method and to provide insights into how the modelling of pixel ownership affects 3D hand pose estimation.
arXiv:2107.00434v2 fatcat:frrzchccbja4pclwkh4ebhposi

Learning To Disambiguate Strongly Interacting Hands via Probabilistic Per-Pixel Part Segmentation

Zicong Fan, Adrian Spurr, Muhammed Kocabas, Siyu Tang, Michael J. Black, Otmar Hilliges
2021 2021 International Conference on 3D Vision (3DV)  
https://zc-alexfan.github.io/digit Figure 1 . When estimating the 3D pose of interacting hands, state-of-the-art methods struggle to disambiguate the appearance of the two hands and their parts. In this example, the baseline fails to differentiate the left and the right wrists (1.1), resulting in erroneous pose estimation (1.2). Our model, DIGIT, reduces the ambiguity by predicting and leveraging a probabilistic part segmentation volume (2.1) to produce reliable pose estimates even when the two
more » ... hands are in direct contact and under significant occlusion (2.2, 2.3).
doi:10.1109/3dv53792.2021.00011 fatcat:l6ozyteqv5dixa7x6vfgnponpq
« Previous Showing results 1 — 15 out of 131 results