Year: 2025
Type: conference-paper
Abstract: In the conversion of night-time infrared videos to visible light, high model complexity and difficult real-time edge deployment pose significant challenges. The existing ROMA model demonstrates excellent performance in generating high fidelity visible-light videos while preserving infrared scene structural information through cross-domain constraints and multi scale discrimination. However, its 16×16 fine-grained patch di vision and 9-layer ResNet lead to substantial computational resource demands during training and inference. To address this, we propose a lightweight framework that collaboratively optimizes large Patch ViT and shallow ResNet. While retaining global structural, local detail, and temporal consistency constraints, the framework significantly reduces self-attention computation and network depth. Experiments on the Infrared City-Lite dataset show that the model achieves competitive FID scores for style authenticity and notably improves computational efficiency. This work provides a lightweight solution for cross-modal conversion in resource constrained environments.
DOI: 10.1117/12.3076886
Authors: Kunyu Li, Shuo Wu, Shijie Wang, Fengqi Yang
Institution: Xi'an Shiyou University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4414216955
FWCI:
Cites:
Cited by:
Related to: