The rapid advancement of artificial intelligence (AI) technology has led to the prioritization of
standardizing the processing, coding, and transmission of video using neural networks. To …

As a fundamental component of video coding, transform coding concentrates the energy
scattered in the spatial domain onto the upper-left region of the frequency domain. This …

Incorporating neural networks into a video codec as an in-loop filter has been shown to
provide significant improvements in coding efficiency. Unfortunately, the computational …

This paper proposes one new In-loop filtering technique cross-component sample adaptive
offset (CCSAO) for further coding efficiency improvement beyond Versatile Video Coding …

Beyond the exploration of traditional spatial, temporal and subjective visual signal
redundancy in image and video compression, recent research has focused on leveraging …

In AV1, for inter coded blocks with compound reference mode, motion vector differences
(MVDs) are signaled for reference frame list 0 or list 1 separately with the same MVD …

It is well-known that non-separable transforms can efficiently decorrelate arbitrarily directed
textures that are often present in image and video content. Due to the computational …

AV1 is a recently proposed video coding standard that significantly improves the video
compression ratio at the same quality as HEVC but at the cost of substantially increasing the …

US11750846B2 - Method and apparatus for video filtering - Google Patents
US11750846B2 - Method and apparatus for video filtering - Google Patents Method and …

Existing cross-component video coding technologies have shown great potential on
improving coding efficiency. The fundamental insight of cross-component coding technology …