Dynamic Frame Interpolation in Wavelet Domain.

Video frame interpolation is an important low-level vision task, which can increase frame rate for more fluent visual experience. Existing methods have achieved great success by employing advanced motion models and synthesis networks. However, the spatial redundancy when synthesizing the target frame has not been fully explored, that can result in lots of inefficient computation. On the other hand, the computation compression degree in frame interpolation is highly dependent on both texture distribution and scene motion, which demands to understand the spatial-temporal information of each input frame pair for a better compression degree selection. In this work, we propose a novel two-stage frame interpolation framework termed WaveletVFI to address above problems. It first estimates intermediate optical flow with a lightweight motion perception network, and then a wavelet synthesis network uses flow aligned context features to predict multi-scale wavelet coefficients with sparse convolution for efficient target frame reconstruction, where the sparse valid masks that control computation in each scale are determined by a crucial threshold ratio. Instead of setting a fixed value like previous methods, we find that embedding a classifier in the motion perception network to learn a dynamic threshold for each sample can achieve more computation reduction with almost no loss of accuracy. On the common high resolution and animation frame interpolation benchmarks, proposed WaveletVFI can reduce computation up to 40% while maintaining similar accuracy, making it perform more efficiently against other state-of-the-arts.

Maternal inheritance of glucose intolerance via oocyte TET3 insufficiency.

Diabetes mellitus is prevalent among women of reproductive age, and many women are left undiagnosed or untreated1. Gestational diabetes has profound and enduring effects on the long-term health of the offspring2,3. However, the link between pregestational diabetes and disease risk into adulthood in the next generation has not been sufficiently investigated. Here we show that pregestational hyperglycaemia renders the offspring more vulnerable to glucose intolerance. The expression of TET3 dioxygenase, responsible for 5-methylcytosine oxidation and DNA demethylation in the zygote4, is reduced in oocytes from a mouse model of hyperglycaemia (HG mice) and humans with diabetes. Insufficient demethylation by oocyte TET3 contributes to hypermethylation at the paternal alleles of several insulin secretion genes, including the glucokinase gene (Gck), that persists from zygote to adult, promoting impaired glucose homeostasis largely owing to the defect in glucose-stimulated insulin secretion. Consistent with these findings, mouse progenies derived from the oocytes of maternal heterozygous and homozygous Tet3 deletion display glucose intolerance and epigenetic abnormalities similar to those from the oocytes of HG mice. Moreover, the expression of exogenous Tet3 mRNA in oocytes from HG mice ameliorates the maternal effect in offspring. Thus, our observations suggest an environment-sensitive window in oocyte development that confers predisposition to glucose intolerance in the next generation through TET3 insufficiency rather than through a direct perturbation of the oocyte epigenome. This finding suggests a potential benefit of pre-conception interventions in mothers to protect the health of offspring.

Direct Access to Allenylphosphine Oxides via a Metal Free Coupling of Propargylic Substrates with P(O)H Compounds.

A direct and convenient approach for the coupling of propargylic substrates with diphenylphosphine oxide in the presence of Tf2O and 2,6-lutidine has been developed. The method provides a general approach for the construction of attractive allenylphosphoryl skeletons with high atom and step economy under metal free conditions.