Bandlet-based sparsity regularization in video inpainting

• Video inpainting by means of spatio-temporal geometric flows extracted by bandlet transform.
• A coarse inpainting is done by a priority-based exemplar scheme enhanced by a bandlet-based patch fusion.
• The inpainting result is refined by a 3D volume regularization algorithm in the bandlet domain.
• The method does not need the conventional processes in order to satisfy visual consistency.
• Effectiveness of our proposed video completion technique and bandlets is demonstrated compared to other methods.

We present a bandlet-based framework for video inpainting in order to complete missing parts of a video sequence. The framework applies spatio-temporal geometric flows extracted by bandlets to reconstruct the missing data. First, a priority-based exemplar scheme enhanced by a bandlet-based patch fusion generates a preliminary inpainting result. Then, the inpainting task is completed by a 3D volume regularization algorithm which takes advantage of bandlet bases in exploiting the anisotropic regularities. The method does not need extra processes in order to satisfy visual consistency. The experimental results demonstrate the effectiveness of our proposed video completion technique.