C Yu, X Bi, Y Fan - Ocean Engineering, 2023 - Elsevier
Deep learning technique, has made tremendous progress in fluid mechanics in recent years, because of its mighty feature extraction capacity from complicated and massive fluid …
Occlusions pose a significant challenge to optical flow algorithms that rely on local evidences. We consider an occluded point to be one that is imaged in the first frame but not …
G Singh, YF Wu, S Ahn - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Unsupervised object-centric learning aims to represent the modular, compositional, and causal structure of a scene as a set of object representations and thereby promises to …
In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency …
Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training …
S Niklaus, F Liu - Proceedings of the IEEE/CVF conference …, 2020 - openaccess.thecvf.com
Differentiable image sampling in the form of backward warping has seen broad adoption in tasks like depth estimation and optical flow prediction. In contrast, how to perform forward …
H Sim, J Oh, M Kim - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
In this paper, we firstly present a dataset (X4K1000FPS) of 4K videos of 1000 fps with the extreme motion to the research community for video frame interpolation (VFI), and propose …
We present a novel method for simultaneous learning of depth, egomotion, object motion, and camera intrinsics from monocular videos, using only consistency across neighboring …
F Zhang, OJ Woodford… - Proceedings of the …, 2021 - openaccess.thecvf.com
Full-motion cost volumes play a central role in current state-of-the-art optical flow methods. However, constructed using simple feature correlations, they lack the ability to encapsulate …