Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Park, Hyoungseob"'
Autor:
Gangopadhyay, Suchisrit, Chen, Xien, Chu, Michael, Rim, Patrick, Park, Hyoungseob, Wong, Alex
We propose UnCLe, a standardized benchmark for Unsupervised Continual Learning of a multimodal depth estimation task: Depth completion aims to infer a dense depth map from a pair of synchronized RGB image and sparse depth map. We benchmark depth comp
Externí odkaz:
http://arxiv.org/abs/2410.18074
Autor:
Zeng, Ziyao, Wu, Yangchao, Park, Hyoungseob, Wang, Daniel, Yang, Fengyu, Soatto, Stefano, Lao, Dong, Hong, Byung-Woo, Wong, Alex
We propose a method for metric-scale monocular depth estimation. Inferring depth from a single image is an ill-posed problem due to the loss of scale from perspective projection during the image formation process. Any scale chosen is a bias, typicall
Externí odkaz:
http://arxiv.org/abs/2410.02924
Autor:
Yang, Fengyu, Feng, Chao, Wang, Daniel, Wang, Tianye, Zeng, Ziyao, Xu, Zhiyang, Park, Hyoungseob, Ji, Pengliang, Zhao, Hanbin, Li, Yuanning, Wong, Alex
Understanding neural activity and information representation is crucial for advancing knowledge of brain function and cognition. Neural activity, measured through techniques like electrophysiology and neuroimaging, reflects various aspects of informa
Externí odkaz:
http://arxiv.org/abs/2407.14020
Autor:
Ezhov, Vadim, Park, Hyoungseob, Zhang, Zhaoyang, Upadhyay, Rishi, Zhang, Howard, Chandrappa, Chethan Chinder, Kadambi, Achuta, Ba, Yunhao, Dorsey, Julie, Wong, Alex
We propose a method for depth estimation under different illumination conditions, i.e., day and night time. As photometry is uninformative in regions under low-illumination, we tackle the problem through a multi-sensor fusion approach, where we take
Externí odkaz:
http://arxiv.org/abs/2405.17315
Autor:
Zeng, Ziyao, Wang, Daniel, Yang, Fengyu, Park, Hyoungseob, Wu, Yangchao, Soatto, Stefano, Hong, Byung-Woo, Lao, Dong, Wong, Alex
Three-dimensional (3D) reconstruction from a single image is an ill-posed problem with inherent ambiguities, i.e. scale. Predicting a 3D scene from text description(s) is similarly ill-posed, i.e. spatial arrangements of objects described. We investi
Externí odkaz:
http://arxiv.org/abs/2404.03635
It is common to observe performance degradation when transferring models trained on some (source) datasets to target testing data due to a domain gap between them. Existing methods for bridging this gap, such as domain adaptation (DA), may require th
Externí odkaz:
http://arxiv.org/abs/2402.03312
Autor:
Yang, Fengyu, Feng, Chao, Chen, Ziyang, Park, Hyoungseob, Wang, Daniel, Dou, Yiming, Zeng, Ziyao, Chen, Xien, Gangopadhyay, Rit, Owens, Andrew, Wong, Alex
The ability to associate touch with other modalities has huge implications for humans and computational systems. However, multimodal learning with touch remains challenging due to the expensive data collection process and non-standardized sensor outp
Externí odkaz:
http://arxiv.org/abs/2401.18084
Unsupervised depth completion and estimation methods are trained by minimizing reconstruction error. Block artifacts from resampling, intensity saturation, and occlusions are amongst the many undesirable by-products of common data augmentation scheme
Externí odkaz:
http://arxiv.org/abs/2310.09739
Federated Learning (FL) is a privacy-preserving distributed machine learning approach geared towards applications in edge devices. However, the problem of designing custom neural architectures in federated environments is not tackled from the perspec
Externí odkaz:
http://arxiv.org/abs/2305.07135
Spiking Neural Networks (SNNs) are recognized as the candidate for the next-generation neural networks due to their bio-plausibility and energy efficiency. Recently, researchers have demonstrated that SNNs are able to achieve nearly state-of-the-art
Externí odkaz:
http://arxiv.org/abs/2304.13098