1-55 of about 55 matches for site:arxiv.org human body
[2406.08858] OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learnin
https://arxiv.org/abs/2406.08858
2406.08858] OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning Skip
https://arxiv.org/abs/2503.15406
2503.15406] Visual Persona: Foundation Model for Full-Body Human Customization Skip to main content We gratefully
https://arxiv.org/abs/2503.15406
2503.15406] Visual Persona: Foundation Model for Full-Body Human Customization Skip to main content We gratefully
https://arxiv.org/abs/2403.04436
2403.04436] Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation Skip to main content We gratefully
https://arxiv.org/abs/2412.13196
propose Advanced Expressive Whole-Body Control (Exbody2), a method for producing whole-body tracking controllers that are
https://arxiv.org/abs/2305.01652
other authors View PDF Abstract: The relatively hot temperature of the human body causes people to
https://arxiv.org/abs/2412.13196
propose Advanced Expressive Whole-Body Control (Exbody2), a method for producing whole-body tracking controllers that are
https://arxiv.org/abs/2311.18836
a process that intertwines image interpretation, world knowledge, and an understanding of body language. Traditional human pose
https://arxiv.org/abs/2311.17857
2311.17857] Gaussian Shell Maps for Efficient 3D Human Generation Skip to main content We gratefully acknowledge
https://arxiv.org/abs/2501.10021
2501.10021] X-Dyna: Expressive Dynamic Human Image Animation Skip to main content We gratefully acknowledge support from the
https://arxiv.org/abs/2501.10021
2501.10021] X-Dyna: Expressive Dynamic Human Image Animation Skip to main content We gratefully acknowledge support from the
https://arxiv.org/abs/2309.17448
2309.17448] SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation Skip to main content We
https://arxiv.org/abs/2310.08579
is that human image is inherently structural over multiple granularities, from the coarse-level body skeleton to fine
https://arxiv.org/abs/2311.17857
2311.17857] Gaussian Shell Maps for Efficient 3D Human Generation Skip to main content We gratefully acknowledge
[2502.01143] ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body
https://arxiv.org/abs/2502.01143
Humanoid robots hold the potential for unparalleled versatility in performing human-like, whole-body skills
https://arxiv.org/abs/2505.02833
Whole-Body Imitation System (TWIST), a system for humanoid teleoperation through whole-body motion imitation. We first
https://arxiv.org/abs/2308.09712
pass, while rarely considering the layer-wise nature of a clothed human body, which often consists
https://arxiv.org/abs/2505.02833
Whole-Body Imitation System (TWIST), a system for humanoid teleoperation through whole-body motion imitation. We first
https://arxiv.org/abs/2409.17280
image. Different from existing methods, Disco4D distinctively disentangles clothings (with Gaussian models) from the human body (with SMPL-X
https://arxiv.org/abs/2402.16796
2402.16796] Expressive Whole-Body Control for Humanoid Robots Skip to main content We gratefully acknowledge support
[2312.08983] Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance
https://arxiv.org/abs/2312.08983
named online full-body motion reaction synthesis, which generates humanoid reactions based on the human actor's motions. The
https://arxiv.org/abs/2501.05420
vision. Its whole-body dexterity allows the robot to utilize its entire body surface for manipulation
https://arxiv.org/abs/2412.17290
since significant viewpoint changes often lead to missing appearance details on the human body. To eliminate
https://arxiv.org/abs/2412.17290
since significant viewpoint changes often lead to missing appearance details on the human body. To eliminate
[2311.18259] Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectiv
https://arxiv.org/abs/2311.18259
2311.18259] Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives Skip to main
https://arxiv.org/abs/2106.04004
2106.04004] Task-Generic Hierarchical Human Motion Prior using VAEs Planned Database Maintenance 2025-09-17 11am-1pm UTC Submission, registration
[2501.04595] MobileH2R: Learning Generalizable Human to Mobile Robot Handover Exclusively from Scala
https://arxiv.org/abs/2501.04595
achieve this, we propose a scalable pipeline for generating diverse synthetic full-body human motion data, an
[2504.03011] Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and H
https://arxiv.org/abs/2504.03011
2504.03011] Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization Skip to main
[2310.01406] HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Gene
https://arxiv.org/abs/2310.01406
01406] HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation Skip to
[2504.03011] Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and H
https://arxiv.org/abs/2504.03011
2504.03011] Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization Skip to main
[2210.01781] COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos
https://arxiv.org/abs/2210.01781
2210.01781] COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos Skip to main content
https://arxiv.org/abs/2204.09443
2204.09443] GIMO: Gaze-Informed Human Motion Prediction in Context Happy Open Access Week from arXiv! YOU make open
[2311.18259] Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectiv
https://arxiv.org/abs/2311.18259
2311.18259] Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives Skip to main
https://arxiv.org/abs/2210.11940
and robot navigation, a deep understanding requires reasoning about human motion and body dynamics over time with
[2503.15586] How to Train Your Dragon: Automatic Diffusion-Based Rigging for Characters with Diverse
https://arxiv.org/abs/2503.15586
experimental) Abstract: Recent diffusion-based methods have achieved impressive results on animating images of human subjects. However, most of
[2503.15586] How to Train Your Dragon: Automatic Diffusion-Based Rigging for Characters with Diverse
https://arxiv.org/abs/2503.15586
experimental) Abstract: Recent diffusion-based methods have achieved impressive results on animating images of human subjects. However, most of
https://arxiv.org/abs/2208.14023
Pose Forecasting with Transformers, by Edward Vendrow and 3 other authors View PDF Abstract: Human pose forecasting is a
https://arxiv.org/abs/2406.10454
to the real world and allows humanoid robots to follow human body and hand
https://arxiv.org/abs/2406.10454
to the real world and allows humanoid robots to follow human body and hand
https://arxiv.org/abs/2204.00604
musical samples conditioned on dance videos. Our proposed framework takes dance video frames and human body motions as input
https://arxiv.org/abs/2204.00604
musical samples conditioned on dance videos. Our proposed framework takes dance video frames and human body motions as input
[2109.06166] Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGA
https://arxiv.org/abs/2109.06166
We first learn to inpaint the correspondence field between the body surface texture and
https://arxiv.org/abs/2505.03729
the simplest way is to just show them-casually capture a human motion video and
https://arxiv.org/abs/2404.01284
Motion Generation, by Mingyuan Zhang and 10 other authors View PDF HTML (experimental) Abstract: Human motion generation, a
https://arxiv.org/abs/2312.04547
capable of engaging in social interactions and expressing with articulated body motions, thereby simulating life
[2109.06166] Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGA
https://arxiv.org/abs/2109.06166
We first learn to inpaint the correspondence field between the body surface texture and
https://arxiv.org/abs/2312.04547
capable of engaging in social interactions and expressing with articulated body motions, thereby simulating life
https://arxiv.org/abs/2307.12067
dataset has many potential applications, such as novel-view synthesis, 3D reconstruction, novel-view acoustic synthesis, human body and face
https://arxiv.org/abs/2410.10803
problem. Our system is mainly an integration of 1) a whole-upper-body robotic teleoperation system to
https://arxiv.org/abs/2410.10803
problem. Our system is mainly an integration of 1) a whole-upper-body robotic teleoperation system to
https://arxiv.org/abs/2306.11932
In particular, we demonstrate with pilot experiments using Anthropic's Claude that LLMs can indeed augment human intelligence to help
https://arxiv.org/abs/2408.00672
or soccer. Our method takes a video demonstration and its accompanying 3D body pose and generates
https://arxiv.org/abs/2303.17912
3D human motion datasets presents a roadblock to creating high-quality generative human motion models. We propose
[2405.04963] Audio Matters Too! Enhancing Markerless Motion Capture with Audio Signals for String Pe
https://arxiv.org/abs/2405.04963
In this paper, we touch on the problem of markerless multi-modal human motion capture especially for
https://arxiv.org/abs/2312.15900
to improve the generation of 3D gestures by utilizing multimodal information from human speech. Previous studies have