# Re-coding for Uncertainties: Edge-awareness Semantic Concordance for Resilient Event-RGB Segmentation Source: [Re-coding for Uncertainties: Edge-awareness Semantic Concordance for Resilient Event-RGB Segmentation]() Collection index: [llms.txt]() Data updated: 2026-03-06T05:00:05.533Z Authors: Nan Bao, Yifan Zhao, Lin Zhu, Jia Li Published: 2025-11-11T14:00:27.000Z ## Abstract Semantic segmentation has achieved great success in ideal conditions. However, when facing extreme conditions (e.g., insufficient light, fierce camera motion), most existing methods suffer from significant information loss of RGB, severely damaging segmentation results. Several researches exploit the high-speed and high-dynamic event modality as a complement, but event and RGB are naturally heterogeneous, which leads to feature-level mismatch and inferior optimization of existing multi-modality methods. Different from these researches, we delve into the edge secret of both modalities for resilient fusion and propose a novel Edge-awareness Semantic Concordance framework to unify the multi-modality heterogeneous features with latent edge cues. In this framework, we first propose Edge-awareness Latent Re-coding, which obtains uncertainty indicators while realigning event-RGB features into unified semantic space guided by re-coded distribution, and transfers event-RGB distributions into re-coded features by utilizing a pre-established edge dictionary as clues. We then propose Re-coded Consolidation and Uncertainty Optimization, which utilize re-coded edge features and uncertainty indicators to solve the heterogeneous event-RGB fusion issues under extreme conditions. We establish two synthetic and one real-world event-RGB semantic segmentation datasets for extreme scenario comparisons. Experimental results show that our method outperforms the state-of-the-art by a 2.55% mIoU on our proposed DERS-XS, and possesses superior resilience under spatial occlusion. Our code and datasets are publicly available at https://github.com/iCVTEAM/ESC. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Semantic Segmentation on DERS-XS (synthetic)](): Semantic segmentation; DERS-XS (synthetic); mACC: 75.26. - [Semantic Segmentation on DERS-XR real-world fine-tuning](): Semantic segmentation; DERS-XR real-world fine-tuning; mACC: 70.75. - [Semantic Segmentation on DSEC Semantic (non-extreme)](): Semantic segmentation; DSEC Semantic (non-extreme); mACC: 78.61. - [Semantic Segmentation on DSEC-Xtrm degraded extreme](): Semantic segmentation; DSEC-Xtrm degraded extreme; mACC: 59.45. ## Original sources and implementation [Original paper]() [PDF]()