BROWSE
Detail
Conference Paper
TSDF-Based Efficient Motion-Compensated Temporal Interpolation for 3D Dynamic Sequences
Cited 0 time in 
Share 
Share
- Authors
- Soowoong Kim, Minseong Kwon, Junho Choi, Gun Bang, Seungjoon Yang
- Issue Date
- 2025-02
- Citation
- The Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence (AAAI) 2025, pp.4311-4319
- Language
- English
- Type
- Conference Paper
- 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 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.
- KSP Keywords
- Computational complexity, Improved Accuracy, Motion prediction, Motion-compensated, Point clouds, Real-Time applications, Signed distance function, Smooth Motion, bi-directional, cloud-based, grid structure