EvDiff3D: Event-Aware Diffusion Repair for High-Fidelity Event-Based 3D Reconstruction
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 2904-2912
DOI: 10.1609/aaai.v40i4.37281 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Kanghao Chen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Event cameras are bio-inspired sensors that capture visual information through asynchronous brightness changes, offering distinct advantages including high temporal resolution and wide dynamic range. While prior research has investigated event-based 3D reconstruction for extreme scenarios, existing methods face inherent limitations and fail to fully exploit the unique characteristics of event data. In this paper, we present EvDiff3D, a novel two-stage 3D reconstruction framework that integrates event-based geometric constraints with an event-aware diffusion prior for appearance refinement. Our key insight lies in bridging the gap between physically grounded event-based reconstruction and data-driven appearance repair through a unified cyclical pipeline. In the first stage, we reconstruct a coarse 3D scene under supervision from event loss and event-based monocular depth constraints to preserve structural fidelity. The second stage fine-tunes an event-aware diffusion model based on a pretrained video diffusion model as a repair prior to enhance the appearance in under-constrained regions. Based on the diffusion model, our pipeline operates within a reconstruction-generation cycle that progressively refines both geometry and appearance using only event data. Extensive experiments on synthetic and real-world datasets demonstrate that EvDiff3D significantly outperforms existing methods in perceptual quality and structural consistency.
Zitieren
APA
Chen, K., Zhang, Z., Li, H., Wang, L., & Wang, Z. (2026). EvDiff3D: Event-Aware Diffusion Repair for High-Fidelity Event-Based 3D Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 2904-2912. https://doi.org/10.1609/aaai.v40i4.37281
Vancouver
Chen K, Zhang Z, Li H, Wang L, Wang Z. EvDiff3D: Event-Aware Diffusion Repair for High-Fidelity Event-Based 3D Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):2904-2912. doi:10.1609/aaai.v40i4.37281
BibTeX
@article{Chen2026,
author = {Chen, Kanghao and Zhang, Zixin and Li, Hangyu and Wang, Lin and Wang, Zeyu},
title = {EvDiff3D: Event-Aware Diffusion Repair for High-Fidelity Event-Based 3D Reconstruction},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {4},
pages = {2904--2912},
doi = {10.1609/aaai.v40i4.37281}
}
EUVIMED