Paper Detail
Hao-Yu Hsu, Tianhang Cheng, Jing Wen, Alexander G. Schwing, Shenlong Wang
Understanding human activities and their surrounding environments typically relies on visual perception, yet cameras pose persistent challenges in privacy, safety, energy efficiency, and scalability. We explore an alternative: 4D perception without vision. Its goal is to reconstruct human motion and 3D scene layouts purely from everyday wearable sensors. For this we introduce IMU-to-4D, a framework that repurposes large language models for non-visual spatiotemporal understanding of human-scene dynamics. IMU-to-4D uses data from a few inertial sensors from earbuds, watches, or smartphones and predicts detailed 4D human motion together with coarse scene structure. Experiments across diverse human-scene datasets show that IMU-to-4D yields more coherent and temporally stable results than SoTA cascaded pipelines, suggesting wearable motion sensors alone can support rich 4D understanding.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{hsu2026seeing,
title = {Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs},
author = {Hao-Yu Hsu and Tianhang Cheng and Jing Wen and Alexander G. Schwing and Shenlong Wang},
year = {2026},
abstract = {Understanding human activities and their surrounding environments typically relies on visual perception, yet cameras pose persistent challenges in privacy, safety, energy efficiency, and scalability. We explore an alternative: 4D perception without vision. Its goal is to reconstruct human motion and 3D scene layouts purely from everyday wearable sensors. For this we introduce IMU-to-4D, a framework that repurposes large language models for non-visual spatiotemporal understanding of human-scene d},
url = {https://arxiv.org/abs/2604.21926},
keywords = {cs.CV},
eprint = {2604.21926},
archiveprefix = {arXiv},
}
{}