Luc Van Gool

TL;DR: In multiple experiments, including ablation studies, it is shown that the proposed model can reliably predict disparity and scene flow in challenging imagery, achieves better generalization than the state-of-the-art, and adapts quickly and robustly to unseen domains.

TL;DR: This paper deals with the computation of a true orthographic image given a set of overlapping perspective images by using a Bayesian approach and defining a generative model of the input images.

TL;DR: This work argues that rela-tionships between compositions go beyond shared states or objects, and proposes a novel method called CAPE, which outperforms previous baselines to set a new state-of-the-art on three publicly available benchmarks.

TL;DR: In this paper , the authors presented a novel micro-ISP model designed specifically for edge devices, taking into account their computational and memory limitations, which is capable of processing up to 32MP photos on recent smartphones using the standard mobile ML libraries and requiring less than 1 second to perform the inference.

TL;DR: In this article, the authors proposed to reparameterize the convolutions of standard neural network architectures into a non-trainable shared part (filter bank) and task-specific parts (modulators), where each modulator has a fraction of the filter bank parameters.