Metraipolis › archive › dc_ec7ab2d5fdf5
LiFR v2: Completion-Augmented Event Propagation for High-Rate Dense Prediction — arXiv:2609.25803
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25803
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T16:39:20.981Z
- SHA-256 of the archived text
3e4e2e6d69c6c701e89bf798c14070dbc113f76a09013d40ec6bffe9f0388f76- Stable URL of this page
https://metraipolis.com/documento/dc_ec7ab2d5fdf5
How to cite
LiFR v2: Completion-Augmented Event Propagation for High-Rate Dense Prediction — arXiv:2609.25803 — arXiv (en), https://arxiv.org/abs/2609.25803 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec7ab2d5fdf5 (Metraipolis archive dc_ec7ab2d5fdf5, sha256 3e4e2e6d69c6c701e89bf798c14070dbc113f76a09013d40ec6bffe9f0388f76)
BibTeX
@misc{dcec7ab2d5fdf5,
title = {LiFR v2: Completion-Augmented Event Propagation for High-Rate Dense Prediction — arXiv:2609.25803},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25803},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec7ab2d5fdf5; sha256 3e4e2e6d69c6c701e89bf798c14070dbc113f76a09013d40ec6bffe9f0388f76},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25803. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
High-rate dense perception in dynamic environments is limited by the low update rate of RGB cameras, as rapid scene changes can occur between frames. Event cameras offer temporally dense but spatially sparse measurements, complementary to spatially dense RGB observations. Direct fusion cannot fully exploit this complementarity, while event-guided propagation fails on newly appearing or disoccluded regions without valid RGB support. We present LiFR v2, a unified propagation-completion-memory framework for causal anytime and streaming dense prediction from an RGB keyframe and events. LiFR v2 introduces an Event-Guided Completion Module (EGCM) to recover task-relevant representations where propagation is unsupported, and a History Retrieval Module (HRM) to reuse completed representations across successive queries. The framework supports semantic segmentation, monocular depth estimation, and multi-task dense prediction, and we further introduce SHF-Emerge to evaluate rapid object emergence and disocclusion. LiFR v2 achieves 74.37% mIoU on DSEC and 56.13% on SHF-Emerge, improving LiFR-Seg by 1.85 percentage points on the latter, while reducing SHF-Emerge depth RMSE from 1.564 m to 1.118 m over the propagation baseline. It also exceeds 100 FPS for both segmentation and depth, demonstrating accurate and efficient high-rate perception beyond RGB frame rates. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.25803 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T15:56:18.144Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).