{"ID":2824503,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.00854","arxiv_id":"2601.00854","title":"Motion-Compensated Latent Semantic Canvases for Visual Situational Awareness on Edge","abstract":"We propose Motion-Compensated Latent Semantic Canvases (MCLSC) for visual situational awareness on resource-constrained edge devices. The core idea is to maintain persistent semantic metadata in two latent canvases - a slowly accumulating static layer and a rapidly updating dynamic layer - defined in a baseline coordinate frame stabilized from the video stream. Expensive panoptic segmentation (Mask2Former) runs asynchronously and is motion-gated: inference is triggered only when motion indicates new information, while stabilization/motion compensation preserves a consistent coordinate system for latent semantic memory. On prerecorded 480p clips, our prototype reduces segmentation calls by \u003e30x and lowers mean end-to-end processing time by \u003e20x compared to naive per-frame segmentation, while maintaining coherent static/dynamic semantic overlays.","short_abstract":"We propose Motion-Compensated Latent Semantic Canvases (MCLSC) for visual situational awareness on resource-constrained edge devices. The core idea is to maintain persistent semantic metadata in two latent canvases - a slowly accumulating static layer and a rapidly updating dynamic layer - defined in a baseline coordin...","url_abs":"https://arxiv.org/abs/2601.00854","url_pdf":"https://arxiv.org/pdf/2601.00854v1","authors":"[\"Igor Lodin\",\"Sergii Filatov\",\"Vira Filatova\",\"Dmytro Filatov\"]","published":"2025-12-29T20:25:02Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}