pith. sign in

arxiv: 2412.01747 · v1 · pith:LFZBV54Inew · submitted 2024-12-02 · 💻 cs.CV

Continuous-Time Human Motion Field from Events

classification 💻 cs.CV
keywords humanmotionfieldcontinuous-timeeventeventsmethodstemporal
0
0 comments X
read the original abstract

This paper addresses the challenges of estimating a continuous-time human motion field from a stream of events. Existing Human Mesh Recovery (HMR) methods rely predominantly on frame-based approaches, which are prone to aliasing and inaccuracies due to limited temporal resolution and motion blur. In this work, we predict a continuous-time human motion field directly from events by leveraging a recurrent feed-forward neural network to predict human motion in the latent space of possible human motions. Prior state-of-the-art event-based methods rely on computationally intensive optimization across a fixed number of poses at high frame rates, which becomes prohibitively expensive as we increase the temporal resolution. In comparison, we present the first work that replaces traditional discrete-time predictions with a continuous human motion field represented as a time-implicit function, enabling parallel pose queries at arbitrary temporal resolutions. Despite the promises of event cameras, few benchmarks have tested the limit of high-speed human motion estimation. We introduce Beam-splitter Event Agile Human Motion Dataset-a hardware-synchronized high-speed human dataset to fill this gap. On this new data, our method improves joint errors by 23.8% compared to previous event human methods while reducing the computational time by 69%.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. LC-Flow: Learning Local Continuous Optical Flow and Confidence from events

    cs.CV 2026-05 unverdicted novelty 7.0

    LC-Flow introduces a continuous local recurrent network for learning sparse optical flow and confidence directly from event streams, with confidence-guided aggregation reaching new SOTA on MVSEC.

  2. MotionMAR: Multi-scale Auto-Regressive Human Motion Reconstruction from Sparse Observations

    cs.CV 2026-06 unverdicted novelty 5.0

    A coarse-to-fine autoregressive framework with multi-scale tokenization and scale-aware control reconstructs human motion from sparse observations and reports SOTA accuracy on AMASS.