Fusing in 3D: Free-Viewpoint Fusion Rendering with a 3D Infrared-Visible Scene Representation
By: Chao Yang , Deshui Miao , Chao Tian and more
Potential Business Impact:
Creates better night-vision pictures from two camera types.
Infrared-visible image fusion aims to integrate infrared and visible information into a single fused image. Existing 2D fusion methods focus on fusing images from fixed camera viewpoints, neglecting a comprehensive understanding of complex scenarios, which results in the loss of critical information about the scene. To address this limitation, we propose a novel Infrared-Visible Gaussian Fusion (IVGF) framework, which reconstructs scene geometry from multimodal 2D inputs and enables direct rendering of fused images. Specifically, we propose a cross-modal adjustment (CMA) module that modulates the opacity of Gaussians to solve the problem of cross-modal conflicts. Moreover, to preserve the distinctive features from both modalities, we introduce a fusion loss that guides the optimization of CMA, thus ensuring that the fused image retains the critical characteristics of each modality. Comprehensive qualitative and quantitative experiments demonstrate the effectiveness of the proposed method.
Similar Papers
MSGFusion: Multimodal Scene Graph-Guided Infrared and Visible Image Fusion
CV and Pattern Recognition
Makes night vision cameras see more details.
Modality-Aware Infrared and Visible Image Fusion with Target-Aware Supervision
CV and Pattern Recognition
Makes cameras see better in fog and dark.
Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws
CV and Pattern Recognition
Makes night vision cameras see clearer details.