arXiv:2209.05993

Sparse Video Representation Using Steered Mixture-of-Experts With Global Motion Compensation

Rolf Jongebloed, Erik Bochinski, Thomas Sikora

제출 2022-09-13

원문 초록

Steered-Mixtures-of Experts (SMoE) present a unified framework for sparse representation and compression of image data with arbitrary dimensionality. Recent work has shown great improvements in the performance of such models for image and light-field representation. However, for the case of videos the straight-forward application yields limited success as the SMoE framework leads to a piece-wise linear representation of the underlying imagery which is disrupted by nonlinear motion. We incorporate a global motion model into the SMoE framework which allows for higher temporal steering of the kernels. This drastically increases its capabilities to exploit correlations between adjacent frames by only adding 2 to 8 motion parameters per frame to the model but decreasing the required amount of kernels on average by 54.25%, respectively, while maintaining the same reconstruction quality yielding higher compression gains.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

arXiv:2507.06085공통 태그 Mixture-of-Experts공식 코드 · Papers with Code

A Survey on Prompt Tuning

토론

이 논문과 연결된 포럼 글이 아직 없습니다.