门怡芳同学论文《DynTypo: Example-based Dynamic Text Effects Transfer》被CVPR 2019录用！
CVPR是计算机视觉、模式识别和人工智能领域国际顶级会议，2019年将在美国加州长滩召开。
本文提出了一种动态纹理特效字形自动生成方法。
门怡芳同学是本论文第一作者，现为实验室二年级硕士研究生。
http://cvpr2019.thecvf.com
Y. Men, Z. Lian*, Y. Tang, J. Xiao. DynTypo: Example-based Dynamic Text Effects Transfer. CVPR 2019 (accepted)
In this paper, we present a novel approach for dynamic
text effects transfer by using example-based texture synthe-
sis. In contrast to previous works that require an input video
of the target to provide motion guidance, we aim to animate
a still image of the target text by transferring the desired
dynamic effects from an observed exemplar. Due to the sim-
plicity of target guidance and complexity of realistic effects,
it is prone to producing temporal artifacts such as flickers
and pulsations. To address the problem, our core idea is
to find a common Nearest-neighbor Field (NNF) that would
optimize the textural coherence across all keyframes simul-
taneously. With the static NNF for video sequences, we
implicitly transfer motion properties from source to target.
We also introduce a guided NNF search by employing the
distance-based weight map and Simulated Annealing (SA)
for deep direction-guided propagation to allow intense dy-
namic effects to be completely transferred with no semantic
guidance provided. Furthermore, generated dynamic texts
can be seamlessly embedded into any static backgrounds
or video clips by poisson image editing. Experimental re-
sults demonstrate the effectiveness and superiority of our
method in dynamic text effects transfer through extensive
comparisons with state-of-the-art algorithms. We also show
the potentiality of our method via multiple experiments for
various application domains.