paper-with-me

홈 › Papers

World-Grounded Human Motion Recovery via Gravity-View Coordinates

2024-09-10 · Zehong Shen, Huaijin Pi, Yan Xia, Zhi Cen, Sida Peng, Zechen Hu, Hujun Bao, Ruizhen Hu, Xiaowei Zhou

We present a novel method for recovering world-grounded human motion from monocular video. The main challenge lies in the ambiguity of defining the world coordinate system, which varies between sequences. Previous approaches attempt to alleviate this issue by predicting relative motion in an autoregressive manner, but are prone to accumulating errors. Instead, we propose estimating human poses in a novel Gravity-View (GV) coordinate system, which is defined by the world gravity and the camera view direction. The proposed GV system is naturally gravity-aligned and uniquely defined for each video frame, largely reducing the ambiguity of learning image-pose mapping. The estimated poses can be transformed back to the world coordinate system using camera rotations, forming a global motion sequence. Additionally, the per-frame estimation avoids error accumulation in the autoregressive methods. Experiments on in-the-wild benchmarks demonstrate that our method recovers more realistic motion in both the camera space and world-grounded settings, outperforming state-of-the-art methods in both accuracy and speed. The code is available at https://zju3dv.github.io/gvhmr/.

📄 PDF Abstract BibTeX arXiv:2409.06662

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Gravity Gravity is a kinematic approach to optimization based on gradients.

Similar Papers 제목 키워드 기반

Force From Motion: Decoding Physical Sensation in a First Person Video

2016-06-01 · CVPR 2016 6 · Hyun Soo Park, Jyh-Jing Hwang, Jianbo Shi

A first-person video can generate powerful physical sensations of action in an observer. In this paper, we focus on a problem of Force from Motion---decoding the sensation of 1) passive forces such as the gravity, 2) the…

Action RecognitionFrictionOptical Flow EstimationTemporal Action Localization

GRAVITY: A Framework for Personalized Text Generation via Profile-Grounded Synthetic Preferences

2025-10-13 · Priyanka Dey, Daniele Rosa, Wenqing Zheng, Daniel Barcklow 외 arxiv

Personalization in LLMs often relies on costly human feedback or interaction logs, limiting scalability and neglecting deeper user attributes. To reduce the reliance on human annotations, we introduce GRAVITY (Generative…

Text Generation

Stubborn: A Streamlined and Unified Reinforcement Learning Framework for Robust Motion Tracking and Fall Recovery for Humanoids

2026-06-11 · Xiao Ren, Yuhui Yang, Zongbiao Weng, Zhijie Liu 외 arxiv

Recent reinforcement learning approaches have shown great promise in improving humanoid motion tracking performance and achieving fall recovery under disturbances. However, most existing works treat motion tracking and f…

Reinforcement Learning

Unified Walking, Running, and Recovery for Humanoids via State-Dependent Adversarial Motion Priors

2026-05-18 · Yidan Lu, Yichao Zhong, Liu Zhao, Wanyue Li 외 arxiv

We propose a unified reinforcement learning framework that enables a single policy to perform walking, running, and fall recovery on the Unitree G1 humanoid robot, validated on physical hardware without any explicit mode…

Reinforcement Learning

WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion

2023-12-12 · CVPR 2024 1 · Soyong Shin, Juyong Kim, Eni Halilaj, Michael J. Black

The estimation of 3D human motion from video has progressed rapidly but current methods still have several key limitations. First, most methods estimate the human in camera coordinates. Second, prior work on estimating h…

3D Human Pose Estimation