Lune

CVPR Findings2026

Generative Event Pretraining with Foundation Model Alignment

Jianwen Cao, Jiaxu Xing, Nico Messikommer, Davide Scaramuzza

Abstract

Event cameras provide robust visual signals under fast motion and challenging illumination thanks to their microsecond latency and high dynamic range. However, their unique sensing characteristics and limited labeled data make it challenging to train event-based visual foundation models (VFMs), which are crucial for learning visual features transferable across tasks. To tackle this problem, we propose GEP (Generative Event Pretraining), a two-stage framework that transfers semantic knowledge learned from internet-scale image datasets to event data while learning event-specific temporal dynamics. First, an event encoder is aligned to a frozen VFM through a joint regressioncontrastive objective, grounding event features in image semantics. Second, a transformer backbone is autoregressively pretrained on mixed event-image sequences to capture the temporal structure unique to events. Our approach outperforms state-of-the-art event pretraining methods on a diverse range of downstream tasks, including object recognition, segmentation, and depth estimation. Together, VFMguided alignment and generative sequence modeling yield a semantically rich, temporally aware event model that generalizes robustly across domains.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • BEiT: BERT Pre-Training of Image Transformers cites A Simple Framework for Contrastive Learning of Visual Representations
  • BEiT: BERT Pre-Training of Image Transformers cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • Efficiently Modeling Long Sequences with Structured State Spaces cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale cites A Simple Framework for Contrastive Learning of Visual Representations
  • Learning Transferable Visual Models From Natural Language Supervision cites A Simple Framework for Contrastive Learning of Visual Representations
  • Learning Transferable Visual Models From Natural Language Supervision cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on18

  1. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
  2. A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 24,064 citations
  3. An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
  4. BEiT: BERT Pre-Training of Image TransformersHangbo Bao, Li Dong, Songhao Piao, Furu WeiICLR 2022 · 3,632 citations
  5. Efficiently Modeling Long Sequences with Structured State SpacesAlbert Gu, Karan Goel, Christopher RéICLR 2022 · 3,482 citations

Related papers

  1. Scaling Dense Event-Stream Pretraining from Visual Foundation ModelsZhiwen Chen, Junhui Hou, Zhiyu Zhu, Jinjian Wu et al.CVPR 2026 · 2 citations
  2. Revealing Latent Information: A Physics-inspired Self-supervised Pre-training Framework for Noisy and Sparse EventsLin Zhu, Ruonan Liu, Xiao Wang, Lizhi Wang et al.ACM MM 2025 · 1 citation
  3. Recurrent Vision Transformers for Object Detection with Event CamerasMathias Gehrig, Davide ScaramuzzaCVPR 2023
  4. Event Camera Data Pre-trainingYan Yang, Liyuan Pan, Liu LiuICCV 2023 · 59 citations
  5. PEPR: Privileged Event-based Predictive Regularization for Domain GeneralizationGabriele Magrini, Federico Becattini, Niccolò Biondi, Pietro PalaCVPR Findings 2026
Dusk over the sea between two cliffs drawn in fine vertical lines