no code implementations • 17 Apr 2024 • Changsuk Oh, Dongseok Shim, Taekbeom Lee, H. Jin Kim
In this letter, to validate the current evaluation methods cannot properly evaluate the performance of an object remover, we create a dataset with object removal ground truth and compare the evaluations made by the current methods using original images to those utilizing object removal ground truth images.
1 code implementation • 5 Mar 2024 • Seungjae Lee, Yibin Wang, Haritheja Etukuru, H. Jin Kim, Nur Muhammad Mahi Shafiullah, Lerrel Pinto
Unlike language or image generation, decision making requires modeling actions - continuous-valued vectors that are multimodal in their distribution, potentially drawn from uncurated sources, where generation errors can compound in sequential prediction.
no code implementations • 30 Oct 2023 • Daesol Cho, Seungjae Lee, H. Jin Kim
Reinforcement learning (RL) often faces the challenges of uninformed search problems where the agent should explore without access to the domain knowledge such as characteristics of the environment or external rewards.
no code implementations • 29 Aug 2023 • Jigang Kim, Dohyun Jang, H. Jin Kim
Deploying multiple robots for target search and tracking has many practical applications, yet the challenge of planning over unknown or partially known targets remains difficult to address.
no code implementations • 8 Aug 2023 • Donggeon David Oh, Dongjae Lee, H. Jin Kim
This study presents a framework to guarantee safety for a class of second-order nonlinear systems under multiple state and input constraints.
1 code implementation • 17 May 2023 • Jigang Kim, Daesol Cho, H. Jin Kim
While reinforcement learning (RL) has achieved great success in acquiring complex skills solely from environmental interactions, it assumes that resets to the initial state are readily available at the end of each episode.
no code implementations • 13 May 2023 • Changsuk Oh, Dongseok Shim, H. Jin Kim
We design the judge module to quantitatively estimate the quality of the object removal results.
Explainable Artificial Intelligence (XAI) Image Inpainting +2
no code implementations • 13 Mar 2023 • Taekbeom Lee, Youngseok Jang, H. Jin Kim
Existence of symmetric objects, whose observation at different viewpoints can be identical, can deteriorate the performance of simultaneous localization and mapping(SLAM).
1 code implementation • 27 Jan 2023 • Daesol Cho, Seungjae Lee, H. Jin Kim
Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed.
no code implementations • 27 Jan 2023 • Dongseok Shim, Seungjae Lee, H. Jin Kim
As previous representations for reinforcement learning cannot effectively incorporate a human-intuitive understanding of the 3D environment, they usually suffer from sub-optimal performances.
1 code implementation • 17 Jan 2023 • Dongseok Shim, H. Jin Kim
Monocular depth estimation plays a critical role in various computer vision and robotics applications such as localization, mapping, and 3D object detection.
1 code implementation • 6 Dec 2022 • Jeongjun Choi, Dongseok Shim, H. Jin Kim
Thanks to the development of 2D keypoint detectors, monocular 3D human pose estimation (HPE) via 2D-to-3D uplifting approaches have achieved remarkable improvements.
Ranked #154 on 3D Human Pose Estimation on Human3.6M
1 code implementation • 11 Oct 2022 • Seungjae Lee, Jigang Kim, Inkyu Jang, H. Jin Kim
Hierarchical Reinforcement Learning (HRL) has made notable progress in complex control tasks by leveraging temporal abstraction.
Hierarchical Reinforcement Learning reinforcement-learning +1
1 code implementation • 30 Sep 2022 • Daesol Cho, Dongseok Shim, H. Jin Kim
Offline reinforcement learning (Offline RL) suffers from the innate distributional shift as it cannot interact with the physical environment during training.
no code implementations • 29 Apr 2022 • Daesol Cho, Jigang Kim, H. Jin Kim
Current reinforcement learning (RL) in robotics often experiences difficulty in generalizing to new downstream tasks due to the innate task-specific training paradigm.
1 code implementation • 5 Apr 2022 • Jigang Kim, J. Hyeon Park, Daesol Cho, H. Jin Kim
Deep reinforcement learning has enabled robots to learn motor skills from environmental interactions with minimal to no prior knowledge.
no code implementations • 10 Mar 2021 • Dongseok Shim, H. Jin Kim
Deep neural networks have been widely studied in autonomous driving applications such as semantic segmentation or depth estimation.
1 code implementation • 12 Nov 2020 • Dongseok Shim, H. Jin Kim
Previous studies on image classification have mainly focused on the performance of the networks, not on real-time operation or model compression.
1 code implementation • 6 Nov 2020 • Dongseok Shim, H. Jin Kim
In this paper, we show that existing self-supervised methods do not perform well on depth estimation and propose a gradient-based self-supervised learning algorithm with momentum contrastive loss to help ConvNets extract the geometric information with unlabeled images.
no code implementations • 18 Sep 2020 • Youngseok Jang, Hojoon Shin, H. Jin Kim
With the dominance of keyframe-based SLAM in the field of robotics, the relative frame poses between keyframes have typically been sacrificed for a faster algorithm to achieve online applications.
no code implementations • 18 Sep 2020 • Haram Kim, Pyojin Kim, H. Jin Kim
The proposed algorithm allows to separate the moving object detection and visual odometry (VO) so that an arbitrary robust VO method can be employed in a dynamic situation with a combination of moving object detection, whereas other VO algorithms for a dynamic environment are inseparable.
no code implementations • 3 Sep 2020 • Boseong Felipe Jeon, Dongseok Shim, H. Jin Kim
The proposed method actively guides the motion of a cinematographer drone so that the color of a target is well-distinguished against the colors of the background in the view of the drone.
no code implementations • 21 Nov 2019 • Boseong Jeon, H. Jin Kim
The proposed system includes 1) a target motion prediction module which can be applied to dense environments and 2) a hierarchical chasing planner based on a proposed metric for visibility.
Robotics
no code implementations • 19 Jul 2019 • Sangil Lee, Clark Youngdong Son, H. Jin Kim
Further, we use a dual-mode motion model to consistently distinguish between the static and dynamic parts in the temporal motion tracking stage.
no code implementations • 17 Jul 2019 • Sangil Lee, Haram Kim, H. Jin Kim
In this work, we propose an edge detection algorithm by estimating a lifetime of an event produced from dynamic vision sensor (DVS), also known as event camera.
Robotics
no code implementations • 6 Apr 2019 • Boseong Felipe Jeon, H. Jin Kim
This work deals with a moving target chasing mission of an aerial vehicle equipped with a vision sensor in a cluttered environment.
Robotics
no code implementations • ECCV 2018 • Pyojin Kim, Brian Coltin, H. Jin Kim
We propose a new formulation for including orthogonal planar features as a global model into a linear SLAM approach based on sequential Bayesian filtering.
no code implementations • CVPR 2018 • Pyojin Kim, Brian Coltin, H. Jin Kim
We propose a novel approach to estimate the three degrees of freedom (DoF) drift-free rotational motion of an RGB-D camera from only a single line and plane in the Manhattan world (MW).