Zobrazeno 1 - 10
of 69
pro vyhledávání: '"Joo, Kyungdon"'
Publikováno v:
IEEE Robotics and Automation Letters (RA-L), vol. 9, no. 12, pp. 11337-11344, Dec. 2024
As service environments have become diverse, they have started to demand complicated tasks that are difficult for a single robot to complete. This change has led to an interest in multiple robots instead of a single robot. C-SLAM, as a fundamental te
Externí odkaz:
http://arxiv.org/abs/2411.14775
Monocular 3D semantic occupancy prediction is becoming important in robot vision due to the compactness of using a single RGB camera. However, existing methods often do not adequately account for camera perspective geometry, resulting in information
Externí odkaz:
http://arxiv.org/abs/2408.03551
Autor:
Shim, Jaehyeok, Joo, Kyungdon
We propose a novel concept of dual and integrated latent topologies (DITTO in short) for implicit 3D reconstruction from noisy and sparse point clouds. Most existing methods predominantly focus on single latent type, such as point or grid latents. In
Externí odkaz:
http://arxiv.org/abs/2403.05005
Publikováno v:
IEEE Robotics and Automation Letters (RA-L), vol. 9, no. 5, pp. 4106-4113, 2024
Indoor scenes we are living in are visually homogenous or textureless, while they inherently have structural forms and provide enough structural priors for 3D scene reconstruction. Motivated by this fact, we propose a structure-aware online signed di
Externí odkaz:
http://arxiv.org/abs/2403.01861
Among various interactions between humans, such as eye contact and gestures, physical interactions by contact can act as an essential moment in understanding human behaviors. Inspired by this fact, given a 3D partner human with the desired interactio
Externí odkaz:
http://arxiv.org/abs/2401.17212
We propose an end-to-end deep learning approach to rectify fisheye images and simultaneously calibrate camera intrinsic and distortion parameters. Our method consists of two parts: a Quick Image Rectification Module developed with a Pix2Pix GAN and W
Externí odkaz:
http://arxiv.org/abs/2305.05222
We propose an end-to-end unified 3D mesh recovery of humans and quadruped animals trained in a weakly-supervised way. Unlike recent work focusing on a single target class only, we aim to recover 3D mesh of broader classes with a single multi-task mod
Externí odkaz:
http://arxiv.org/abs/2111.02450
Stereo-LiDAR fusion is a promising task in that we can utilize two different types of 3D perceptions for practical usage -- dense 3D information (stereo cameras) and highly-accurate sparse point clouds (LiDAR). However, due to their different modalit
Externí odkaz:
http://arxiv.org/abs/2103.12964
This paper presents a stereo object matching method that exploits both 2D contextual information from images as well as 3D object-level information. Unlike existing stereo matching methods that exclusively focus on the pixel-level correspondence betw
Externí odkaz:
http://arxiv.org/abs/2103.12498
In this paper, we propose a robust and efficient end-to-end non-local spatial propagation network for depth completion. The proposed network takes RGB and sparse depth images as inputs and estimates non-local neighbors and their affinities of each pi
Externí odkaz:
http://arxiv.org/abs/2007.10042