no code implementations • ECCV 2020 • Woobin Im, Tae-Kyun Kim, Sung-Eui Yoon
Deep unsupervised learning for optical flow has been proposed, where the loss measures image similarity with the warping function parameterized by estimated flow.
1 code implementation • 12 Mar 2024 • Jumin Lee, Sebin Lee, Changho Jo, Woobin Im, Juhyeong Seon, Sung-Eui Yoon
In this paper, we concentrate on generating a real-outdoor scene through learning a diffusion model on a real-world outdoor dataset.
1 code implementation • 8 Mar 2024 • Youngju Na, Woo Jae Kim, Kyu Beom Han, Suhyeon Ha, Sung-Eui Yoon
Generalizable neural implicit surface reconstruction aims to obtain an accurate underlying geometry given a limited number of multi-view images from unseen scenes.
1 code implementation • 11 Oct 2023 • Kyuyeon Kim, Junsik Jung, Woo Jae Kim, Sung-Eui Yoon
To implement the prior knowledge, we first train the audio-visual network, which learns the correspondence between auditory and visual information.
1 code implementation • ICCV 2023 • Guoyuan An, Woo Jae Kim, Saelyne Yang, Rong Li, Yuchi Huo, Sung-Eui Yoon
To this end, we propose pixel retrieval benchmarks named PROxford and PRParis, which are based on the widely used image retrieval datasets, ROxford and RParis.
1 code implementation • 11 Apr 2023 • Kyu Beom Han, Olivia G. Odenthal, Woo Jae Kim, Sung-Eui Yoon
Then we design our ensembling network to obtain per-pixel ensembling weight maps, which represent pixel-wise guidance for which auxiliary feature should be dominant at reconstructing each individual pixel and use them to ensemble the two denoised results of our denosiers.
1 code implementation • CVPR 2023 • Woo Jae Kim, Yoonki Cho, Junsik Jung, Sung-Eui Yoon
The Separation part disentangles the input feature map into the robust feature with activations that help the model make correct predictions and the non-robust feature with activations that are responsible for model mispredictions upon adversarial attack.
no code implementations • 14 Feb 2023 • Pei Wang, Danna Xue, Yu Zhu, Jinqiu Sun, Qingsen Yan, Sung-Eui Yoon, Yanning Zhang
For general scene deblurring, the feature space of the blurry image and corresponding sharp image under the high-level vision task is closer, which inspires us to rely on other tasks (e. g. classification) to learn a comprehensive prior in severe blur removal cases.
1 code implementation • 2 Jan 2023 • Jumin Lee, Woobin Im, Sebin Lee, Sung-Eui Yoon
To the best of our knowledge, our work is the first to apply discrete and latent diffusion for 3D categorical data on a scene-scale.
1 code implementation • 1 Oct 2022 • Xu Yin, Dongbo Min, Yuchi Huo, Sung-Eui Yoon
This novel module transfers the predicted/ground-truth semantic labels to a self-defined potential domain to learn and infer decision boundaries along customized directions.
1 code implementation • 11 Aug 2022 • Woo Jae Kim, Seunghoon Hong, Sung-Eui Yoon
Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality.
1 code implementation • 21 Jul 2022 • Woobin Im, Sebin Lee, Sung-Eui Yoon
A training pipeline for optical flow CNNs consists of a pretraining stage on a synthetic dataset followed by a fine tuning stage on a target dataset.
1 code implementation • CVPR 2022 • Yoonki Cho, Woo Jae Kim, Seunghoon Hong, Sung-Eui Yoon
In this paper, we propose a novel Part-based Pseudo Label Refinement (PPLR) framework that reduces the label noise by employing the complementary relationship between global and part features.
Ranked #3 on Unsupervised Vehicle Re-Identification on VeRi-776
1 code implementation • NeurIPS 2021 • Guoyuan An, Yuchi Huo, Sung-Eui Yoon
However, existing query expansion and diffusion methods cannot efficiently propagate the spatial information in an ordinary graph with scalar edge weights, resulting in low recall or precision.
Ranked #1 on Image Retrieval on RParis (Medium)
1 code implementation • 26 Jun 2021 • Changho Jo, Woobin Im, Sung-Eui Yoon
Our self-supervision method, In-N-Out, is summarized as a training approach that leverages the knowledge of the opposite task into the target model.
no code implementations • 15 Jan 2020 • Mingi Lim, Sung-Eui Yoon
In this paper, we propose a deep learning-based reflectance map prediction system for material estimation of target objects in the image, so as to alleviate the ill-posed problem that occurs in this image decomposition operation.
no code implementations • 28 Oct 2019 • Seongjae Kang, Jaeyoon Kim, Sung-Eui Yoon
Especially for detecting intensity, a new method of utilizing spatial, temporal CNNs model is devised.
no code implementations • 16 Sep 2019 • Tae-Young Kim, Youngsun Kwon, Sung-Eui Yoon
This paper proposes a real-time system integrating an acoustic material estimation from visual appearance and an on-the-fly mapping in the 3-dimension.
no code implementations • 26 Aug 2019 • Hongsun Choi, Mincheul Kang, Youngsun Kwon, Sung-Eui Yoon
We propose a novel method utilizing an objectness score for maintaining the locations and classes of objects detected from Mask R-CNN during mobile robot navigation.
1 code implementation • 24 Jul 2019 • Nitin Agarwal, Sung-Eui Yoon, M Gopi
Sharp features such as edges and corners play an important role in the perception of 3D models.
no code implementations • 11 Jul 2019 • Chiwan Song, Woobin Im, Sung-Eui Yoon
Understanding the content of videos is one of the core techniques for developing various helpful applications in the real world, such as recognizing various human actions for surveillance systems or customer behavior analysis in an autonomous shop.
no code implementations • 6 Jul 2019 • JaeWon Choi, Sung-Eui Yoon
At an early age, human infants are able to learn and build a model of the world very quickly by constantly observing and interacting with objects around them.
1 code implementation • CVPR 2020 • Soo-Min Kim, Yuchi Huo, Sung-Eui Yoon
Recently, deep learning-based single image reflection separation methods have been exploited widely.
no code implementations • 19 Sep 2018 • Yuchi Huo, Sung-Eui Yoon
We introduce an optical neural network system made by off-the-shelf components.
no code implementations • CVPR 2016 • Jae-Pil Heo, Zhe Lin, Xiaohui Shen, Jonathan Brandt, Sung-Eui Yoon
We have tested the proposed method with the inverted index and multi-index on a diverse set of benchmarks including up to one billion data points with varying dimensions, and found that our method robustly improves the accuracy of shortlists (up to 127% relatively higher) over the state-of-the-art techniques with a comparable or even faster computational cost.
no code implementations • CVPR 2014 • Jae-Pil Heo, Zhe Lin, Sung-Eui Yoon
This result is achieved mainly because our method accurately estimates distances between two data points with the new binary codes and distance metric.