Signals 4 · free daily AI digest

InfiniHand: Streaming World-Space Hand Motion Estimation from Egocentric Video

Paper recorded by Signals 4 on 2026-09-28 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-28 on arXiv · recorded by Signals 4 on 2026-09-29

Category: cs.CV · 计算机视觉 · first seen 2026-09-29

Abstract

World-space hand motion estimation from egocentric video requires recovering 3D articulated hand geometry while tracking camera egomotion. Existing approaches heavily rely on cascading independent hand pose estimators and SLAM systems, resulting in error accumulation, complex pipelines, and severe computational overhead. To address these limitations, we present InfiniHand, an end-to-end streaming

Read on arXiv →

#2 most recent of 342 cs.CV papers we have recorded · ↑ newer: Reliability-Gated Fusion of Consumer Head and Foot IMUs for Lower-Body · ↓ older: GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Sp
Cite this page: InfiniHand: Streaming World-Space Hand Motion Estimation from Egocentric Video: the #2 most recent of 342 cs.CV papers we have recorded (as of 2026-09-28). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/infinihand-streaming-world-space-hand-motion-estimation-from-egocentric-video.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions