all AI news
FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation. (arXiv:2305.03327v1 [cs.CV])
cs.CV updates on arXiv.org arxiv.org
Current video text spotting methods can achieve preferable performance,
powered with sufficient labeled training data. However, labeling data manually
is time-consuming and labor-intensive. To overcome this, using low-cost
synthetic data is a promising alternative. This paper introduces a novel video
text synthesis technique called FlowText, which utilizes optical flow
estimation to synthesize a large amount of text video data at a low cost for
training robust video text spotters. Unlike existing methods that focus on
image-level synthesis, FlowText concentrates on …
arxiv cost data flow labeling labor low novel optical flow paper performance synthesis synthetic synthetic data text text synthesis training training data video