Patch Tracking-based Streaming Tensor Ring Completion for Visual Data Recovery

TL;DR

This paper introduces a novel patch tracking-based streaming tensor ring completion method for visual data recovery, effectively handling large motion in videos by dynamically tracking patches and completing missing data.

Contribution

The paper proposes a new patch tracking strategy and a streaming tensor ring completion algorithm tailored for sequential visual data with dynamic changes.

Findings

Outperforms state-of-the-art tensor completion methods in experiments

Accurately tracks patches with missing data in streaming videos

Efficiently updates tensor cores for real-time visual data recovery

Abstract

Tensor completion aims to recover the missing entries of a partially observed tensor by exploiting its low-rank structure, and has been applied to visual data recovery. In applications where the data arrives sequentially such as streaming video completion, the missing entries of the tensor need to be dynamically recovered in a streaming fashion. Traditional streaming tensor completion algorithms treat the entire visual data as a tensor, which may not work satisfactorily when there is a big change in the tensor subspace along the temporal dimension, such as due to strong motion across the video frames. In this paper, we develop a novel patch tracking-based streaming tensor ring completion framework for visual data recovery. Given a newly incoming frame, small patches are tracked from the previous frame. Meanwhile, for each tracked patch, a patch tensor is constructed by stacking similar patches from the new frame. Patch tensors are then completed using a streaming tensor ring completion algorithm, and the incoming frame is recovered using the completed patch tensors. We propose a new patch tracking strategy that can accurately and efficiently track the patches with missing data. Further, a new streaming tensor ring completion algorithm is proposed which can efficiently and accurately update the latent core tensors and complete the missing entries of the patch tensors. Extensive experimental results demonstrate the superior performance of the proposed algorithms compared with both batch and streaming state-of-the-art tensor completion methods.