A team of researchers has released a tool they call “Depth-Aware Video Frame Interpolation” or DAIN, which is capable of turning regular footage into “fragment less” slow-mo.
The team behind it combined scientists from Wenbo Bao of Shanghai Jiao Tong University and researchers from the University of California Merced as well as Google.
“Video frame interpolation aims to synthesize non-existent frames in-between the original frames. While significant advances have been made from the deep convolutional neural networks, the quality of interpolation is often reduced due to large object motion or occlusion. In this work, we propose to explicitly detect the occlusion by exploring the depth cue in frame interpolation. Specifically, we develop a depth-aware flow projection layer to synthesize intermediate flows that preferably sample closer objects than farther ones. In addition, we learn hierarchical features as the contextual information.”
In other words, their tool fills in the missing information using an array of datasets to make it natural looking.
The abstract continues:
“The proposed model then warps the input frames, depth maps, and contextual features based on the optical flow and local interpolation kernels for synthesizing the output frame. Our model is compact, efficient, and fully differentiable to optimize all the components. We conduct extensive experiments to analyze the effect of the depth-aware flow projection layer and hierarchical contextual features. Quantitative and qualitative results demonstrate that the proposed model performs favorably against state-of-the-art frame interpolation methods on a wide variety of datasets.”
You can watch a video explaining it here.
And, in case you missed it, here's a recent article we posted about Microsoft's AI that detects edits in photos.
What do you think of this AI tool? Let us know your thoughts on this article in the comments section below if you like.
Don’t forget to check out our other photography news articles on Light Stalking by clicking here.