DeLux: Cross-Modal Local Artifact Restoration in Video Using Neuromorphic Data
Quick Answer
DeLux introduces a cross-modal restoration method using neuromorphic event streams to effectively reduce lighting artifacts in RGB video, achieving an average MS-SSIM of over 0.99 and an 88% reduction in artifact severity in real-world footage.
Quick Take
DeLux introduces a cross-modal restoration method using neuromorphic event streams to effectively reduce lighting artifacts in RGB video, achieving an average MS-SSIM of over 0.99 and an 88% reduction in artifact severity in real-world footage. This approach outperforms existing RGB-only and event-guided HDR models, providing a significant advancement in video restoration techniques.
Key Points
- DeLux uses neuromorphic data to guide artifact detection and inpainting.
- Achieves over 0.99 MS-SSIM across all artifact types in benchmarks.
- Demonstrates up to 88% reduction in artifact severity in automotive footage.
- Publicly available tools for synthetic artifact generation and evaluation datasets.
- Outperforms existing RGB-only baselines and event-guided HDR models.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Conventional RGB cameras suffer from lighting artifacts such as flare, glare, flicker, and overexposure, leading to irrecoverable information loss that necessitates computational restoration. However, existing approaches treat these problems in isolation, failing to recover structural details completely obscured by complex spatially discrete image degradations. In this paper, we propose a novel cross-modal restoration paradigm and present DeLux, a modular proof-of-concept pipeline that leverages neuromorphic event streams as a structural prior to guide the targeted detection and inpainting of lighting artifacts in RGB video. Validation on synthetic benchmarks and real-world automotive footage demonstrates that DeLux effectively suppresses local artifacts and restores affected regions. The proposed approach outperforms existing RGB-only baselines and event-guided HDR models, achieving an average MS-SSIM of over 0.99 across all artifact types and demonstrating up to an 88% reduction in artifact severity in real-world automotive footage. The synthetic artifact generation tools and curated real-world evaluation datasets are made publicly available to foster future research on cross-modal restoration.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2606.27576 [cs.CV] |
| (or arXiv:2606.27576v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2606.27576 arXiv-issued DOI via DataCite |
Submission history
From: Dariusz Brzezinski [view email]
[v1]
Thu, 25 Jun 2026 22:03:43 UTC (17,634 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.