Motion-Compensated Latent Semantic Canvases for Visual Situational Awareness on Edge

Igor Lodin, Sergii Filatov, Vira Filatova, Dmytro Filatov
12/29/2025
cs.CV

No confident code implementation found for this paper.

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 >30x and lowers mean end-to-end processing time by >20x compared to naive per-frame segmentation, while maintaining coherent static/dynamic semantic overlays.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

4DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threads

83% match1 repo72025

LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment

82% match1 repo922026

M2H: Multi-Task Learning with Efficient Window-Based Cross-Task Attention for Monocular Spatial Perception

81% match2025

MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds

81% match1 repo682026

SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes

80% match1 repo222026

2nd Place Solution for PVUW Challenge 2024: Video Panoptic Segmentation

80% match2024

Cite this paper

@article{lodin2025motioncompensated,
  title  = {Motion-Compensated Latent Semantic Canvases for Visual Situational Awareness on Edge},
  author = {Igor Lodin and Sergii Filatov and Vira Filatova and Dmytro Filatov},
  year   = {2025},
  eprint = {2601.00854},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2601.00854v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2601.00854.svg)](https://codeofpaper.com/paper/2601.00854)

Discussion