Hybrid error concealment method combining exemplar-based image inpainting and spatial interpolation

•We propose hybrid error concealment method combining image inpainting and spatial interpolation.•We propose an adaptive threshold by local complexity for selecting inpainting or interpolation.•We propose an exemplar-based image inpainting method including side matching distortion.•We propose a spatial interpolation method selecting directional or neighbor interpolation.•The proposed method gives substantial quality improvements compared with the previous methods.

This paper proposes an efficient error concealment method for the reconstruction of pixels that are lost in video communication. The proposed method is developed by combining exemplar-based image inpainting for patch reconstruction and spatial interpolation for pixel reconstruction using adaptive threshold by local complexity. By exemplar-based image inpainting, regions with regular structures are reconstructed. For complex regions with irregular structures, just one pixel is reconstructed using the proposed spatial interpolation method. The proposed spatial interpolation method performs reconstruction by selecting adaptively directional interpolation or neighbor interpolation based on gradient information. Simulation results show that the proposed hybrid method performs reconstruction with significantly improved subjective quality compared with the previous spatial error concealment and image inpainting methods. The proposed method also gives substantial improvements of PSNR compared with the previous methods.