Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Kocabas, Muhammed"'
Publikováno v:
WACV 2024
Understanding how humans interact with the world necessitates accurate 3D hand pose estimation, a task complicated by the hand's high degree of articulation, frequent occlusions, self-occlusions, and rapid motions. While most existing methods rely on
Externí odkaz:
http://arxiv.org/abs/2312.16737
Autor:
Kocabas, Muhammed, Yuan, Ye, Molchanov, Pavlo, Guo, Yunrong, Black, Michael J., Hilliges, Otmar, Kautz, Jan, Iqbal, Umar
We present a method to estimate human motion in a global scene from moving cameras. This is a highly challenging task due to the coupling of human and camera motions in the video. To address this problem, we propose a joint optimization framework tha
Externí odkaz:
http://arxiv.org/abs/2310.13768
We propose a physics-based method for synthesizing dexterous hand-object interactions in a full-body setting. While recent advancements have addressed specific facets of human-object interactions, a comprehensive physics-based approach remains a chal
Externí odkaz:
http://arxiv.org/abs/2309.07907
We present a method for inferring diverse 3D models of human-object interactions from images. Reasoning about how humans interact with objects in complex scenes from a single 2D image is a challenging task given ambiguities arising from the loss of i
Externí odkaz:
http://arxiv.org/abs/2209.02485
We introduce TempCLR, a new time-coherent contrastive learning approach for the structured regression task of 3D hand reconstruction. Unlike previous time-contrastive methods for hand pose estimation, our framework considers temporal consistency in i
Externí odkaz:
http://arxiv.org/abs/2209.00489
Autor:
Fan, Zicong, Taheri, Omid, Tzionas, Dimitrios, Kocabas, Muhammed, Kaufmann, Manuel, Black, Michael J., Hilliges, Otmar
Humans intuitively understand that inanimate objects do not move by themselves, but that state changes are typically caused by human manipulation (e.g., the opening of a book). This is not yet the case for machines. In part this is because there exis
Externí odkaz:
http://arxiv.org/abs/2204.13662
Autor:
Yi, Hongwei, Huang, Chun-Hao P., Tzionas, Dimitrios, Kocabas, Muhammed, Hassan, Mohamed, Tang, Siyu, Thies, Justus, Black, Michael J.
Humans are in constant contact with the world as they move through it and interact with it. This contact is a vital source of information for understanding 3D humans, 3D scenes, and the interactions between them. In fact, we demonstrate that these hu
Externí odkaz:
http://arxiv.org/abs/2203.03609
We introduce the dynamic grasp synthesis task: given an object with a known 6D pose and a grasp reference, our goal is to generate motions that move the object to a target 6D pose. This is challenging, because it requires reasoning about the complex
Externí odkaz:
http://arxiv.org/abs/2112.03028
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 b
Externí odkaz:
http://arxiv.org/abs/2110.03480
Autor:
Kocabas, Muhammed, Huang, Chun-Hao P., Tesch, Joachim, Müller, Lea, Hilliges, Otmar, Black, Michael J.
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
Externí odkaz:
http://arxiv.org/abs/2110.00620