cs.CVNov 18, 2026

ALIVE: Bring Foundation Features to Life with Events

Authors: Rong Zou, Haiqing Hao, Davide Scaramuzza

Organizations: Robotics and Perception Group, University of Zurich · Tsinghua University

Abstract

Visual foundation models provide powerful representations for diverse tasks, but their features become stale as visual content changes between image observations. Refreshing them requires new frames and repeated runs of a computationally expensive image encoder. We introduce ALIVE, an event-based method that incrementally updates native foundation model features between image observations. Given an anchor image, ALIVE uses subsequent events to transport and correct existing multi-layer features extracted by a frozen DINOv3 encoder. Its lightweight updater is trained end-to-end using only synthetic data, without downstream task supervision, and transfers directly to real-world event streams without any adaptation. Across three real-world datasets and five task-dataset settings spanning object detection, semantic segmentation, and depth estimation, ALIVE outperforms all evaluated event-based methods in every metric. On DSEC, when the anchor frame is 200,ms old, ALIVE improves over anchor-image predictions by 30.9,mAP in detection, 11.6,mIoU in segmentation, and 15.9% in depth AbsRel. Compared with image re-encoding, ALIVE reduces FLOPs by 82.4% and latency by a factor of 2.5.

Figures & tables

Explore similar work

CardsList
  1. REALM: An RGB- and Event-Aligned Latent Manifold for Cross-Modal Perception

    Apr 30, 2026Vincenzo Polizzi, David B. Lindell, Jonathan KellyMultimodal Foundation ModelsEvent-Based Vision

  2. Generative Event Pretraining with Foundation Model Alignment

    Mar 24, 2026Jianwen Cao, Jiaxu Xing, Nico Messikommer +1Event-Based VisionVision Foundation Model Adaptation

  3. Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras

    Apr 20, 2026Ruijun Zhang, Hang Su, Kostas Daniilidis +1Event-Based VisionDomain Generalization