Total Directional Variation for Video Denoising
This work addresses video denoising for applications requiring preservation of anisotropic structures, but the extension is incremental as it adapts an existing image denoising method to video without introducing new theoretical insights.
The paper extends the total directional variation (TDV) regularizer from image to video denoising by incorporating a volumetric structure tensor to capture space-time structures. The proposed method achieves competitive denoising performance compared to state-of-the-art techniques, though no specific numerical gains are reported.
In this paper, we propose a variational approach for video denoising, based on a total directional variation (TDV) regulariser proposed in Parisotto et al. (2018), for image denoising and interpolation. In the TDV regulariser, the underlying image structure is encoded by means of weighted derivatives so as to enhance the anisotropic structures in images, e.g. stripes or curves with a dominant local directionality. For the extension of TDV to video denoising, the space-time structure is captured by the volumetric structure tensor guiding the smoothing process. We discuss this and present our whole video denoising work-flow. Our numerical results are compared with some state-of-the-art video denoising methods.