Search AI Products and News

Facing the direct impact of video quality on viewing experience, especially regarding the presentation of facial details, current methods such as simply applying super-resolution networks to face datasets or independently processing each frame often struggle to balance the detail of facial reconstruction with temporal consistency. To address this challenge, the research team at Nanyang Technological University has launched the innovative framework KEEP, which utilizes the principles of Kalman filtering to achieve a 'memory' capability in facial restoration, significantly enhancing the consistency and continuity of facial details during the restoration process. The KEEP framework consists of four key modules: Encoder, Decoder, Kalman.

In the field of video production and image processing, the "de-flicker" technology has always been crucial for enhancing video quality. With the advancement of technology, a new de-flicker algorithm called BlazeBVD has emerged, capable of not only quickly removing flicker from videos but also maintaining the integrity and color authenticity of the video content. BlazeBVD, short for Blaze Blind Video Deflickering, is an automated video de-flicker technology. It can effectively improve the tempora