RESTORATION OF EXTREMELY COMPRESSED BACKGROUND FOR VCM USING GUIDED GENERATIVE PRIORS
Le Thi Hue Dao, An Gia Vien, Jooyoung Lee, Seyoon Jeong, Chul Lee
-
SPS
IEEE Members: $11.00
Non-members: $15.00
We propose a learning-based image restoration algorithm for a single decoded image with a high-quality foreground and an extremely degraded background for video coding for machines (VCM). First, we develop an encoder that extracts multiscale features and learns latent vectors. Then, a background generator with style and feature fusion blocks generates guided features that contain the prior background information in the input image. Finally, the decoder restores the degraded background region by merging the image features from the encoder and prior background information from the generator. Experimental results show that the proposed algorithm achieves better performance than state-of-the-art algorithms.