TranSR-NeRF: Super-resolution neural radiance field for reconstruction and rendering of weak and repetitive texture of aviation damaged functional surface

Abstract

In order to reconstruct and render the weak and repetitive texture of the damaged functional surface of aviation, an improved neural radiance field, named TranSR-NeRF, is proposed. In this paper, a data acquisition system was designed and built. The acquired images generated initial point clouds through TransMVSNet. Meanwhile, after extracting features from the images through the improved SE-ConvNeXt network, the extracted features were aligned and fused with the initial point cloud to generate high-quality neural point cloud. After ray-tracing and sampling of the neural point cloud, the ResMLP neural network designed in this paper was used to regress the volume density and radiance under a given viewing angle, which introduced spatial coordinate and relative positional encoding. The reconstruction and rendering of arbitrary-scale super-resolution of damaged functional surface is realized. In this paper, the influence of illumination conditions and background environment on the model performance is also studied through experiments, and the comparison and ablation experiments for the improved methods proposed in this paper is conducted. The experimental results show that the improved model has good effect. Finally, the application experiment of object detection task is carried out, and the experimental results show that the model has good practicability.