Boosting Neural Representations for Videos with a Conditional Decoder

arXiv:2402.18152v1 Announce Type: cross
Abstract: Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks. However, existing methods often fail to fully leverage their representation capabilities, primarily due to inadequate alignment of intermediate features during target frame decoding. This paper introduces a universal boosting framework for current implicit video representation approaches. Specifically, we utilize a conditional decoder with a temporal-aware affine transform module, which uses the frame index …

abstract alignment arxiv boosting capabilities cs.ai cs.cv decoder decoding eess.iv features implicit neural representations intermediate processing representation storage tasks type video videos