Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟱𝟭 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 Stable Long-Term Recurrent Video Super-Resolution Follow me for a similar post: 🇮🇳 Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 Paper: Stable Long-Term Recurrent Video Super-Resolution 🔸 This paper is published in arxiv2021. 🔸 Pointed out the divergence prob- lem of recurrent VSR when facing long sequences with low motion. Existing recurrent VSR networks generate high- frequency artifacts on such sequences. To solve this is- sue, we defined a new framework of recurrent VSR model, based on Lipschitz stability theory. As an implementation of this framework, we proposed a new recurrent VSR net- work coined MRVSR. We experimentally verified its sta- bility and state-of-the-art performance on long sequences with low motion. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔹Recurrent models have gained popularity in deep learning (DL) based video super-resolution (VSR), due to their increased computational efficiency, temporal receptive field and temporal consistency compared to sliding-window based models. 🔸However, when inferring on long video sequences presenting low motion (i.e. in which some parts of the scene barely move), recurrent models diverge through recurrent processing, generating high frequency artifacts. 🔹To the best of our knowledge, no study about VSR pointed out this instability problem, which can be critical for some real-world applications. 🔸Video surveillance is a typical example where such artifacts would occur, as both the camera and the scene stay static for a long time. 🔹In this work, we expose instabilities of existing recurrent VSR networks on long sequences with low motion. We demonstrate it on a new long sequence dataset Quasi-Static Video Set, that we have created. 🔸Finally, we introduce a new framework of recurrent VSR networks that is both stable and competitive, based on Lipschitz stability theory. We propose a new recurrent VSR network, coined Middle Recurrent Video Super-Resolution (MRVSR), based on this framework. We empirically show its competitive performance on long sequences with low motion. ------------------------------------------------------------------- #computervision #artificialintelligence #innovation -------------------------------------------------------------------