John Seon Keun Yi

Mr. John Seon Keun Yi

Georgia Institute of Technology
orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2023
Verified
Conference Paper
Open access
PDF file
CZChaoning Zhang
Chaoning Zhang
CZChenshuang Zhang
Chenshuang Zhang
JSJunha Song
Junha Song
JYJohn Seon Keun Yi
John Seon Keun Yi
In So KweonIn So Kweon
In So Kweon
With the increasing popularity of masked autoencoders, self-supervised learning (SSL) in vision undertakes a similar trajectory as in NLP. Specifically, generative pretext tasks with the masked prediction have become a de facto standard SSL practice in NLP (e.g., BERT). By contrast, early attempts at generative methods in vision have been outperformed by their discriminative counterparts (like contrastive learning). However, the success of masked image modeling has revived the autoencoder-based visual pretraining method. As a milestone to bridge the gap with BERT in NLP, masked autoencoder in vision has attracted unprecedented attention. This work conducts a survey on masked autoencoders for visual SSL.

4 September 2020 in Sensors
Verified
Journal Article
Open access
PDF file
Jingdao ChenJingdao Chen
Jingdao Chen
JYJohn Seon Keun Yi
John Seon Keun Yi
MKMark Kahoush
Mark Kahoush
Erin ChoErin Cho
Erin Cho
YCYong Kwon Cho
Yong Kwon Cho
Collecting 3D point cloud data of buildings is important for many applications such as urban mapping, renovation, preservation, and energy simulation. However, laser-scanned point clouds are often difficult to analyze, visualize, and interpret due to incompletely scanned building facades caused by numerous sources of defects such as noise, occlusions, and moving objects. Several point cloud scene completion algorithms have been proposed in the literature, but they have been mostly applied to individual objects or small-scale indoor environments and not on large-scale scans of building facades. This paper introduces a method of performing point cloud scene completion of building facades using orthographic projection and generative adversarial inpainting methods. The point cloud is first converted into the 2D structured representation of depth and color images using an orthographic projection approach. Then, a data-driven 2D inpainting approach is used to predict the complete version of the scene, given the incomplete scene in the image domain. The 2D inpainting process is fully automated and uses a customized generative-adversarial network based on Pix2Pix that is trainable end-to-end. The inpainted 2D image is finally converted back into a 3D point cloud using depth remapping. The proposed method is compared against several baseline methods, including geometric methods such as Poisson reconstruction and hole-filling, as well as learning-based methods such as the point completion network (PCN) and TopNet. Performance evaluation is carried out based on the task of reconstructing real-world building facades from partial laser-scanned point clouds. Experimental results using the performance metrics of voxel precision, voxel recall, position error, and color error showed that the proposed method has the best performance overall.

1 November 2012
Verified
Conference Paper
Closed access
MSMin Hoi Song
Min Hoi Song
JYJohn Seon Keun Yi
John Seon Keun Yi
SYSeokjoo Yoo
Seokjoo Yoo
KKKyu Hyuk Kim
Kyu Hyuk Kim
JSJong Tae Seo
Jong Tae Seo
BYByung-Ju Yi
Byung-Ju Yi
Automobile technologies are developing over time, and one of the main aspects of development is about safety, which is about preventing and minimizing the danger of accidents. This paper focuses on one of the most cutting edge automobile safety technologies: Adaptive Cruise Control(ACC), and expands it by using a number of sensors to inspect omni-directions of the vehicle. Three kinds of experiments were conducted to test the results of Omni-directional Adaptive Cruise Control(OACC).