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.
@article{arxiv.2504.12899,
title = {Tree-NeRV: A Tree-Structured Neural Representation for Efficient Non-Uniform Video Encoding},
author = {Jiancheng Zhao and Yifan Zhan and Qingtian Zhu and Mingze Ma and Muyao Niu and Zunian Wan and Xiang Ji and Yinqiang Zheng},
journal= {arXiv preprint arXiv:2504.12899},
year = {2025}
}