PulseAugur
EN
LIVE 10:01:06

SemanticXR enables low-power, real-time semantic mapping for XR

Researchers have developed SemanticXR, a novel device-cloud architecture for real-time, low-power semantic mapping in Extended Reality (XR) applications. This system treats identifiable objects as primary units for communication, execution, and memory management across both the device and the cloud. SemanticXR significantly improves mapping latency and reduces bandwidth requirements while maintaining low power consumption on the device. AI

IMPACT This system could enable more sophisticated and responsive AI assistants and spatial search capabilities within XR environments.

RANK_REASON The cluster describes a research paper detailing a new system architecture for a specific application domain.

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 English(EN) · Rahul Singh, Devdeep Ray, Connor Smith, Sarita Adve ·

    SemanticXR: Low Power and Real-time Queryable Semantic Mapping with an Object-Level Device-Cloud Architecture

    arXiv:2606.12849v1 Announce Type: cross Abstract: Semantic mapping is a core service that enables grounded interactions in emerging Extended Reality (XR) applications such as AI assistants and spatial object search. Deploying this capability on mobile XR devices requires a system…

  2. arXiv cs.CV TIER_1 English(EN) · Sarita Adve ·

    SemanticXR: Low Power and Real-time Queryable Semantic Mapping with an Object-Level Device-Cloud Architecture

    Semantic mapping is a core service that enables grounded interactions in emerging Extended Reality (XR) applications such as AI assistants and spatial object search. Deploying this capability on mobile XR devices requires a system that is open-vocabulary, real-time, and low-power…