Take a Prior from Other Tasks for Severe Blur Removal
https://sgvr.kaist.ac.kr/publication/take-a-prior-from-other-tasks-for-severe-blur-removal/
Pei Wang, Yu Zhu, Danna Xue, Qingsen Yan, Jinqiu Sun, Sung-eui Yoon, and Yanning Zhang
Computer Vision and Image Understanding (CVIU), 2024
Recovering clear structures from severely blurry inputs is a huge challenge due to the detail loss and ambiguous semantics. Although segmentation maps can help deblur facial images, their effectiveness is … Continue reading "Take a Prior from Other Tasks for Severe Blur Removal"
UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets
https://sgvr.kaist.ac.kr/publication/uforecon/
Youngju Na, Woo Jae Kim, Kyu Beom Han, Suhyeon Ha, and Sung-Eui Yoon
TopIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Topological RANSAC for instance verification and retrieval without fine-tuning
https://sgvr.kaist.ac.kr/publication/topological-ransac-for-instance-verification-and-retrieval-without-fine-tuning/
Guoyuan An, Juhyung Seon, InKyu An, Yuchi Huo, and Sung-Eui Yoon
TopThirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023
행동 Scene-Graph 예측기를 활용한 시나리오 생성Scenario Generation by Action Scene-Graph Prediction
https://sgvr.kaist.ac.kr/publication/ksc2022/
Woobin Im, Woo Jae Kim, and Sung-Eui Yoon
한국소프트웨어종합학술대회 (KSC), 2022
Abstract 본 연구는 행동 예측기를 통해서 시나리오를 생성하는 문제를 탐구한다. 시나리오란 행동의 시퀀스로서, 소셜로봇이 사용자와 협업을 수행하는 데 이용될 수 있다. 하지만 수집된 데이터만으로는 시나리오의 종류가 한정적이기 때문에 다양한 시나리오를 … Continue reading "행동 Scene-Graph 예측기를 활용한 시나리오 생성"
Contour-Aware Equipotential Learning for Semantic Segmentation
https://sgvr.kaist.ac.kr/publication/contour-aware-equipotential-learning-for-semantic-segmentation/
Xu Yin, Dongbo Min, Yuchi Huo, and Sung-Eui Yoon
IEEE Transactions on Multimedia (TMM), 2022
Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attacks
https://sgvr.kaist.ac.kr/publication/icip2022-ada/
Woo Jae Kim, Seunghoon Hong, and Sung-Eui Yoon
IEEE International Conference on Image Processing (ICIP), 2022
Oral paper
arXiv GitHub Slides
Part-based Pseudo Label Refinement for Unsupervised Person Re-identification
https://sgvr.kaist.ac.kr/publication/part-based-pseudo-label-refinement-for-unsupervised-person-re-identification/
Yoonki Cho, Woo Jae Kim, Seunghoon Hong, and Sung-Eui Yoon
TopIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Deep Video Inpainting Guided by Audio-Visual Self-Supervision
https://sgvr.kaist.ac.kr/publication/deep-video-inpainting-guided-by-audio-visual-self-supervision-2/
Kyuyeon Kim, Junsik Jung, Woo Jae Kim, and Sung-Eui Yoon
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022
In-N-Out: Towards Good Initialization for Inpainting and Outpainting
https://sgvr.kaist.ac.kr/publication/bmvc2021-in-n-out/
Changho Jo, Woobin Im, and Sung-Eui Yoon
British Machine Vision Conference (BMVC), 2021
Abstract In computer vision, recovering spatial information by filling in masked regions, e.g., inpainting, has been widely investigated for its usability and wide applicability to other various applications: image inpainting, … Continue reading "In-N-Out: Towards Good Initialization for Inpainting and Outpainting"
Hypergraph Propagation and Community Selection for Objects Retrieval
https://sgvr.kaist.ac.kr/publication/hypergraph-propagation-and-community-selection-for-objects-retrieval/
Guoyuan An, Yuchi Huo, and Sung-Eui Yoon
Top35th Conference on Neural Information Processing Systems (NeurIPS), 2021
Unsupervised Learning of Optical Flow with Deep Feature Similarity
https://sgvr.kaist.ac.kr/publication/unsupsimflow/
Woobin Im, Tae-Kyun Kim, and Sung-Eui Yoon
TopEuropean Conference on Computer Vision (ECCV), 2020
Single Image Reflection Removal with Physically-Based Training Images
https://sgvr.kaist.ac.kr/publication/single-image-reflection-removal-with-physically-based-training-images/
Soomin Kim, Yuchi Huo, and Sung-Eui Yoon
TopComputer Vision and Pattern Recognition (CVPR), 2020
Oral paper
Real-time 3-D Mapping with Estimating Acoustic Materials
https://sgvr.kaist.ac.kr/publication/real-time-3-d-mapping-with-estimating-acoustic-materials/
Taeyoung Kim, Youngsun Kwon, and Sung-eui Yoon
IEEE/SICE International Symposium on System Integration (SII), 2020
An Objectness Score for Accurate and Fast Detection during Navigation
https://sgvr.kaist.ac.kr/publication/an-objectness-score-for-accurate-and-fast-detection-during-navigation/
Hongsun Choi, Mincheul Kang, Youngsun Kwon, and Sung-eui Yoon
The World Congress on Advances in Nano, Bio, Robotics and Energy (ANBRE), 2019
Two-stream Spatiotemporal Feature for Video QA Task
https://sgvr.kaist.ac.kr/publication/two-stream-spatiotemporal-feature-for-video-qa-task/
Chiwan Song, Woobin Im, and Sung-eui Yoon
Arxiv, 2019
Coarse-to-Fine Clothing Image Generation with Progressively Constructed Conditional GAN
https://sgvr.kaist.ac.kr/publication/coarse-to-fine-clothing-image-generation-with-progressively-constructed-conditional-gan/
Youngki Kwon, Soomin Kim, Donggeun Yoo, and Sung-Eui Yoon
International Conference on Computer Vision Theory and Application (VISAPP), 2019