Tree-NeRV: A Tree-Structured Neural Representation for Efficient Non-Uniform Video Encoding
This work addresses inefficiencies in video encoding for applications like streaming or storage, though it appears incremental as it builds on existing NeRV paradigms with a novel structural adaptation.
The paper tackles the problem of suboptimal rate-distortion performance in implicit neural video representations by proposing Tree-NeRV, a tree-structured method that enables non-uniform sampling along the temporal axis, achieving superior compression efficiency and reconstruction quality compared to prior uniform sampling-based methods.
Implicit Neural Representations for Videos (NeRV) have emerged as a powerful paradigm for video representation, enabling direct mappings from frame indices to video frames. However, existing NeRV-based methods do not fully exploit temporal redundancy, as they rely on uniform sampling along the temporal axis, leading to suboptimal rate-distortion (RD) performance. To address this limitation, we propose Tree-NeRV, a novel tree-structured feature representation for efficient and adaptive video encoding. Unlike conventional approaches, Tree-NeRV organizes feature representations within a Binary Search Tree (BST), enabling non-uniform sampling along the temporal axis. Additionally, we introduce an optimization-driven sampling strategy, dynamically allocating higher sampling density to regions with greater temporal variation. Extensive experiments demonstrate that Tree-NeRV achieves superior compression efficiency and reconstruction quality, outperforming prior uniform sampling-based methods. Code will be released.