AbstractSince RANSAC, a great deal of research has been devoted to improving both its accuracy and run-time. Still, only few methods aim at recognizing invalid minimal samples early, before the often expensive model estimation quality calculation are done. To this end, we propose NeFSAC, an efficient algorithm for neural filtering motion-inconsistent poorly-conditioned samples. We train NeFSAC ...

Kappa is a language geared towards the modelling of the complex systems of reactions that can occur between proteins inside cells. It is supported by sophisticated simulation and static analysis techniques which can be applied to the models to study their emergent behaviour. Part of this is the construction by the simulator of causal histories explaining the generation of patterns of connectivi...

We present a novel shadow smoothing algorithm using the bilateral filter. From the observation that shadow leaking, which is found often in filter based approaches, occurs at depth discontinuity seen from the viewpoint of the eye, we apply the bilateral filter which is conceptually a product of two Gaussian filters, one for smoothing the shadow map and the other for handling depth discontinuity...