IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation

Advanced video frame interpolation (VFI) algorithms approximate intermediate motions between two input frames to synthesize intermediate frame. However, they struggle to handle complex scenarios with curvilinear motions since they overlook the latent acceleration information between the input frames. Moreover, the supervision of predicted motions is tricky because ground-truth motions are not available. To this end, we propose a novel framework for implicit quadratic video frame interpolation (IQ-VFI), which explores latent acceleration information and accurate intermediate motions via knowledge distillation. Specifically, the proposed IQ-VFI consists of an implicit acceleration estimation network (IANet) and a VFI backbone, the former fully leverages spatio-temporal information to explore latent acceleration priors between two input frames, which is then used to progressively modulate linear motions from the latter into quadratic motions in coarseto-fine manner. Furthermore, to encourage both components to distill more acceleration and motion cues oriented towards VFI, we propose a knowledge distillation strategy in which implicit acceleration distillation loss and implicit motion distillation loss are employed to adaptively guide latent acceleration priors and intermediate motions learning, respectively. Extensive experiments show that our proposed IQ-VFI can achieve state-of-the-art performances on various benchmark datasets. † Corresponding Author Time step 𝒕 𝟎 𝒕 𝟏 (a) Time step 𝒕 𝟎 𝒕 𝟏 (b) 𝒕 𝟎.𝟓 𝒕 𝟎.𝟓