TSDF-Based Efficient Motion-Compensated Temporal Interpolation for 3D Dynamic Sequences
Abstract
This paper introduces a method for efficiently interpolating 3D dynamic sequences using truncated signed distance function (TSDF) volumes. The method calculates bi-directional motions between TSDF volumes of two frames and refines them to reconstruct intermediate frames. Unlike point cloud-based methods, which can suffer from varying and irregular point densities, the uniform and dense grid structure of TSDF offers a consistent framework for estimating the true motion of objects within a scene. In our experiments, the TSDF-based method offers more precise and reliable smooth motion prediction compared to the often error-prone surface depiction in point clouds. Experimental results demonstrate improved accuracy and reduced computational complexity, making it suitable for real-time applications.
Cite
Text
Kim et al. "TSDF-Based Efficient Motion-Compensated Temporal Interpolation for 3D Dynamic Sequences." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I4.32453Markdown
[Kim et al. "TSDF-Based Efficient Motion-Compensated Temporal Interpolation for 3D Dynamic Sequences." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/kim2025aaai-tsdf/) doi:10.1609/AAAI.V39I4.32453BibTeX
@inproceedings{kim2025aaai-tsdf,
title = {{TSDF-Based Efficient Motion-Compensated Temporal Interpolation for 3D Dynamic Sequences}},
author = {Kim, Soowoong and Kwon, Minseong and Choi, Junho and Bang, Gun and Yang, Seungjoon},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {4311-4319},
doi = {10.1609/AAAI.V39I4.32453},
url = {https://mlanthology.org/aaai/2025/kim2025aaai-tsdf/}
}