paper-with-me

홈 › Papers

FootFormer: Estimating Stability from Visual Input

2025-10-22 · Keaton Kraiger, Jingjing Li, Skanda Bharadwaj, Jesse Scott, Robert T. Collins, Yanxi Liu arxiv

We propose FootFormer, a cross-modality approach for jointly predicting human motion dynamics directly from visual input. On multiple datasets, FootFormer achieves statistically significantly better or equivalent estimates of foot pressure distributions, foot contact maps, and center of mass (CoM), as compared with existing methods that generate one or two of those measures. Furthermore, FootFormer achieves SOTA performance in estimating stability-predictive components (CoP, CoM, BoS) used in classic kinesiology metrics. Code and data are available at https://github.com/keatonkraiger/Vision-to-Stability.git.

📄 PDF Abstract BibTeX arXiv:2510.19170

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation

2026-05-22 · Junwen Tan, Jinglin Liang, Hongyuan Chen, Shuangping Huang arxiv

Though rectified flow models have achieved remarkable performance in image, video, and 3D generation, their practical deployments are challenged by slow inference speeds. Prior acceleration methods reuse cached features …

Video Generation3D Generation

Analyzing Stability of Convolutional Neural Networks in the Frequency Domain

2015-11-10 · Elnaz J. Heravi, Hamed H. Aghdam, Domenec Puig

Understanding the internal process of ConvNets is commonly done using visualization techniques. However, these techniques do not usually provide a tool for estimating the stability of a ConvNet against noise. In this pap…

Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training

2023-08-13 · ICCV 2023 1 · Xiao-Ming Wu, Dian Zheng, Zuhao Liu, Wei-Shi Zheng

Binarization of neural networks is a dominant paradigm in neural networks compression. The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also caus…

Binarization

Adaptive Actor-Critic Based Optimal Regulation for Drift-Free Uncertain Nonlinear Systems

2024-06-13 · Ashwin P. Dani, Shubhendu Bhasin

In this paper, a continuous-time adaptive actor-critic reinforcement learning (RL) controller is developed for drift-free nonlinear systems. Practical examples of such systems are image-based visual servoing (IBVS) and w…

Reinforcement Learning (RL)

Hybrid Controller for Robot Manipulators in Task-Space with Visual-Inertial Feedback

2023-11-20 · Seyed Hamed Hashemi, Jouni Mattila

This paper presents a visual-inertial-based control strategy to address the task space control problem of robot manipulators. To this end, an observer-based hybrid controller is employed to control end-effector motion. I…