Exploiting Semantic Information and Deep Matching for Optical Flow
Citations
2,231 citations
579 citations
Cites background or methods from "Exploiting Semantic Information and..."
...As mentioned above, Bai et al. (2016) extract traffic participants using instance-level segmentation and estimate the optical flow independently for different instances....
[...]
...When the goal is to represent real-world scenes with independent object motion as in scene flow or optical flow, superpixels can be generalized to rigidly moving segments (Vogel et al. (2015); Menze & Geiger (2015)), or semantic segments (Bai et al. (2016); Sevilla-Lara et al. (2016))....
[...]
...(2016)) or use semantic segmentation to split the scene into independently moving objects Bai et al. (2016); Sevilla-Lara et al....
[...]
...(Bai et al. (2016); Sevilla-Lara et al. (2016)) and learned highcapacity models (Dosovitskiy et al. (2015); Ranjan & Black (2016); Ilg et al. (2016)) have already proven to improve optical flow estimation by resolving ambiguities in the data....
[...]
...(Bai et al. (2016); Sevilla-Lara et al. (2016)) and learned highcapacity models (Dosovitskiy et al. (2015); Ranjan & Black (2016); Ilg et al....
[...]
422 citations
356 citations
Cites background from "Exploiting Semantic Information and..."
...Other works attempt to exploit semantic segmentation information to help optical flow estimation [37, 1, 19], e....
[...]
329 citations
Cites background from "Exploiting Semantic Information and..."
...[2] tackled instance-level segmentation and epipolar constraints to reduce the uncertainty of optical flow estimation....
[...]
References
111,197 citations
46,906 citations
30,843 citations
17,184 citations
[...]
14,824 citations