SelFlow: Self-Supervised Learning of Optical Flow — mentioned by fxtentacle

Wed, 10 Jun 2020 15:11:20 GMT

Here's the optical flow paper considered worldwide state of the art for drone navigation: https://arxiv.org/abs/2003.13045 4x Zhejiang University, Hangzhou, China 6x Tencent's Youtu Lab, Shenzhen, China Before that was released, the previous state of the art was: https://arxiv.org/abs/1904.09117 3x The Chinese University of Hong Kong 1x Tencent AI Lab, Shenzhen, China In Sintel, a benchmark performed by a German university, both of these also rank higher than the highest-ranked research team including a US citizen. It may not be what people want to hear and/or it maybe an issue of cheating…

Paper and discussion history. A mention is not an endorsement.

SelFlow: Self-Supervised Learning of Optical Flow — mentioned by fxtentacle

Fri, 03 Jan 2020 20:42:58 GMT

It used to be. Then the AI fanboys arrived and started treating it like a learning problem. https://arxiv.org/abs/1612.01925 https://arxiv.org/abs/1709.02371 https://arxiv.org/abs/1904.09117 BTW, also the classical algorithms deal very badly with noise and repetitive textures, e.g. a video of a forest in the afternoon.

Paper and discussion history. A mention is not an endorsement.

SelFlow: Self-Supervised Learning of Optical Flow · HackerPapers discussions

SelFlow: Self-Supervised Learning of Optical Flow — mentioned by fxtentacle

SelFlow: Self-Supervised Learning of Optical Flow — mentioned by fxtentacle