DerainNeRF: 3D Scene Estimation with Adhesive Waterdrop Removal
This addresses image quality degradation for computer vision applications in rainy or snowy conditions, representing an incremental improvement in adhesive waterdrop removal.
The paper tackles the problem of reconstructing clear 3D scenes from multi-view images degraded by waterdrops on glass, using an attention network and Neural Radiance Fields to remove waterdrops and render high-quality novel-view images, outperforming existing state-of-the-art methods in experiments on synthetic and real datasets.
When capturing images through the glass during rainy or snowy weather conditions, the resulting images often contain waterdrops adhered on the glass surface, and these waterdrops significantly degrade the image quality and performance of many computer vision algorithms. To tackle these limitations, we propose a method to reconstruct the clear 3D scene implicitly from multi-view images degraded by waterdrops. Our method exploits an attention network to predict the location of waterdrops and then train a Neural Radiance Fields to recover the 3D scene implicitly. By leveraging the strong scene representation capabilities of NeRF, our method can render high-quality novel-view images with waterdrops removed. Extensive experimental results on both synthetic and real datasets show that our method is able to generate clear 3D scenes and outperforms existing state-of-the-art (SOTA) image adhesive waterdrop removal methods.