no code implementations • 6 Apr 2024 • Gwanghyun Kim, Hayeon Kim, Hoigi Seo, Dong Un Kang, Se Young Chun
We propose BeyondScene, a novel framework that overcomes prior limitations, generating exquisite higher-resolution (over 8K) human-centric scenes with exceptional text-image correspondence and naturalness using existing pretrained diffusion models.
no code implementations • 20 Dec 2023 • Byung Hyun Lee, Min-hwan Oh, Se Young Chun
Specifically, for input perturbation, we propose an approximate perturbation method that injects noise into the input data as well as the feature vector and then interpolates the two perturbed samples.
no code implementations • 12 Dec 2023 • Tom Tirer, Raja Giryes, Se Young Chun, Yonina C. Eldar
Yet, in many cases there is value in training a network just from the input at hand.
no code implementations • 4 Dec 2023 • Heejun Shin, Taehee Kim, Jongho Lee, Se Young Chun, Seungryung Cho, Dongmyung Shin
In the FACT method, we meta-trained a neural network and a hash-encoder using a few scans (= 15), and a new regularization technique is utilized to reconstruct the details of an anatomical structure.
no code implementations • 30 Nov 2023 • Gwanghyun Kim, Dong Un Kang, Hoigi Seo, Hayeon Kim, Se Young Chun
Text-driven large scene image synthesis has made significant progress with diffusion models, but controlling it is challenging.
no code implementations • 30 Nov 2023 • Seongmin Hong, Kyeonghyun Lee, Suh Yoon Jeon, Hyewon Bae, Se Young Chun
Diffusion probabilistic models (DPMs) are a key component in modern generative models.
no code implementations • 2 Nov 2023 • Haechang Lee, Wongi Jeong, Dongil Ryu, Hyunwoo Je, Albert No, Kijeong Kim, Se Young Chun
In this study, we aim to bridge the gap by exploring extremely low-bit lightweight face detectors, focusing on the always-on face detection scenario for mobile image sensor applications.
no code implementations • ICCV 2023 • Byung Hyun Lee, Okchul Jung, Jonghyun Choi, Se Young Chun
To address this challenge, we propose a novel multi-level hierarchical class incremental task configuration with an online learning constraint, called hierarchical label expansion (HLE).
no code implementations • ICCV 2023 • Haechang Lee, Dongwon Park, Wongi Jeong, Kijeong Kim, Hyunwoo Je, Dongil Ryu, Se Young Chun
Our KLAP and KLAP-M methods achieved state-of-the-art demosaicing performance in both synthetic and real RAW data of Bayer and non-Bayer CFAs.
1 code implementation • 7 Apr 2023 • Seongmin Hong, Se Young Chun
In this work, we propose diffeomorphic non-uniform B-spline flows that are at least twice continuously differentiable while bi-Lipschitz continuous, enabling efficient parametrization while retaining analytic inverse transforms based on a sufficient condition for diffeomorphism.
no code implementations • 6 Apr 2023 • Hoigi Seo, Hayeon Kim, Gwanghyun Kim, Se Young Chun
Our DITTO-NeRF consists of constructing high-quality partial 3D object for limited in-boundary (IB) angles using the given or text-generated 2D image from the frontal view and then iteratively reconstructing the remaining 3D NeRF using inpainting latent diffusion model.
no code implementations • ICCV 2023 • Gwanghyun Kim, Ji Ha Jang, Se Young Chun
However, adapting 3D generators to domains with significant domain gaps from the source domain still remains challenging due to issues in current text-to-image diffusion models as following: 1) shape-pose trade-off in diffusion-based translation, 2) pose bias, and 3) instance bias in the target domain, resulting in inferior 3D shapes, low text-image correspondence, and low intra-domain diversity in the generated samples.
no code implementations • CVPR 2023 • Dongwon Park, Byung Hyun Lee, Se Young Chun
Image restorations for single degradations have been widely studied, demonstrating excellent performance for each degradation, but can not reflect unpredictable realistic environments with unknown multiple degradations, which may change over time.
no code implementations • ICCV 2023 • Seongmin Hong, Inbum Park, Se Young Chun
Most normalizing flows for inverse problems in imaging employ the conditional affine coupling layer that can generate diverse images quickly.
no code implementations • CVPR 2023 • Gwanghyun Kim, Se Young Chun
Here we propose DATID-3D, a domain adaptation method tailored for 3D generative models using text-to-image diffusion models that can synthesize diverse images per text prompt without collecting additional images and camera information for the target domain.
no code implementations • 7 Nov 2022 • Andrey Ignatov, Grigory Malivenko, Radu Timofte, Lukasz Treszczotko, Xin Chang, Piotr Ksiazek, Michal Lopuszynski, Maciej Pioro, Rafal Rudnicki, Maciej Smyl, Yujie Ma, Zhenyu Li, Zehui Chen, Jialei Xu, Xianming Liu, Junjun Jiang, XueChao Shi, Difan Xu, Yanan Li, Xiaotao Wang, Lei Lei, Ziyu Zhang, Yicheng Wang, Zilong Huang, Guozhong Luo, Gang Yu, Bin Fu, Jiaqi Li, Yiran Wang, Zihao Huang, Zhiguo Cao, Marcos V. Conde, Denis Sapozhnikov, Byeong Hyun Lee, Dongwon Park, Seongmin Hong, Joonhee Lee, Seunggyu Lee, Se Young Chun
Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks.
2 code implementations • 7 Nov 2022 • Andrey Ignatov, Radu Timofte, Maurizio Denna, Abdel Younes, Ganzorig Gankhuyag, Jingang Huh, Myeong Kyun Kim, Kihwan Yoon, Hyeon-Cheol Moon, Seungho Lee, Yoonsik Choe, Jinwoo Jeong, Sungjei Kim, Maciej Smyl, Tomasz Latkowski, Pawel Kubik, Michal Sokolski, Yujie Ma, Jiahao Chao, Zhou Zhou, Hongfan Gao, Zhengfeng Yang, Zhenbing Zeng, Zhengyang Zhuge, Chenghua Li, Dan Zhu, Mengdi Sun, Ran Duan, Yan Gao, Lingshun Kong, Long Sun, Xiang Li, Xingdong Zhang, Jiawei Zhang, Yaqi Wu, Jinshan Pan, Gaocheng Yu, Jin Zhang, Feng Zhang, Zhe Ma, Hongbin Wang, Hojin Cho, Steve Kim, Huaen Li, Yanbo Ma, Ziwei Luo, Youwei Li, Lei Yu, Zhihong Wen, Qi Wu, Haoqiang Fan, Shuaicheng Liu, Lize Zhang, Zhikai Zong, Jeremy Kwon, Junxi Zhang, Mengyuan Li, Nianxiang Fu, Guanchen Ding, Han Zhu, Zhenzhong Chen, Gen Li, Yuanfan Zhang, Lei Sun, Dafeng Zhang, Neo Yang, Fitz Liu, Jerry Zhao, Mustafa Ayazoglu, Bahri Batuhan Bilecen, Shota Hirose, Kasidis Arunruangsirilert, Luo Ao, Ho Chun Leung, Andrew Wei, Jie Liu, Qiang Liu, Dahai Yu, Ao Li, Lei Luo, Ce Zhu, Seongmin Hong, Dongwon Park, Joonhee Lee, Byeong Hyun Lee, Seunggyu Lee, Se Young Chun, Ruiyuan He, Xuhao Jiang, Haihang Ruan, Xinjian Zhang, Jing Liu, Garas Gendy, Nabil Sabor, Jingchao Hou, Guanghui He
While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints.
no code implementations • 16 Aug 2022 • Juhyung Park, Dongwon Park, Hyeong-Geol Shin, Eun-Jung Choi, Hongjun An, Minjun Kim, Dongmyung Shin, Se Young Chun, Jongho Lee
Hence, methods such as Noise2Noise (N2N) that require only pairs of noise-corrupted images have been developed to reduce the burden of obtaining training datasets.
no code implementations • 4 Jul 2022 • Okchul Jung, Dong Un Kang, Gwanghyun Kim, Se Young Chun
The experimental results show that the proposed method improve the detection performance with large margin without much difficult modification to the model.
no code implementations • 10 May 2022 • Il Yong Chun, Dongwon Park, Xuehang Zheng, Se Young Chun, Yong Long
Regression that predicts continuous quantity is a central part of applications using computational imaging and computer vision technologies.
no code implementations • 29 Sep 2021 • Il Yong Chun, Dongwon Park, Xuehang Zheng, Se Young Chun, Yong Long
Regression that predicts continuous quantity is a central part of applications using computational imaging and computer vision technologies.
1 code implementation • ICCV 2021 • Yeonsik Jo, Se Young Chun, Jonghyun Choi
Deep image prior (DIP) serves as a good inductive bias for diverse inverse problems.
no code implementations • 4 Feb 2021 • Shady Abu-Hussein, Tom Tirer, Se Young Chun, Yonina C. Eldar, Raja Giryes
In the first one, where no explicit prior is used, we show that the proposed approach outperforms other internal learning methods, such as DIP.
no code implementations • 23 Dec 2020 • Dongwon Park, Dong Un Kang, Se Young Chun
Secondly, we propose multi-blurring recurrent neural network (MBRNN) that can synthesize more blurred images from neighboring frames, yielding substantially improved performance with existing video deblurring methods.
Ranked #5 on Deblurring on DVD (using extra training data)
no code implementations • CVPR 2021 • Kwanyoung Kim, Dongwon Park, Kwang In Kim, Se Young Chun
Often, labeling large amount of data is challenging due to high labeling cost limiting the application domain of deep learning techniques.
1 code implementation • ECCV 2020 • Dongwon Park, Dong Un Kang, Jisoo Kim, Se Young Chun
Multi-scale (MS) approaches have been widely investigated for blind single image / video deblurring that sequentially recovers deblurred images in low spatial scale first and then in high spatial scale later with the output of lower scales.
Ranked #14 on Deblurring on HIDE (trained on GOPRO)
no code implementations • 16 Sep 2019 • Dongwon Park, Yonghyeok Seo, Dongju Shin, Jaesik Choi, Se Young Chun
Recently, robotic grasp detection (GD) and object detection (OD) with reasoning have been investigated using deep neural networks (DNNs).
no code implementations • 25 Mar 2019 • Dongwon Park, Jisoo Kim, Se Young Chun
Our proposed CNN-based down-scaling was the key factor for this excellent performance since the performance of our network without it was decreased by 1. 98dB.
no code implementations • 7 Feb 2019 • Byung Hyun Lee, Se Young Chun
Recently, deep neural networks (DNNs) have shown advantages in accelerating optimization algorithms.
1 code implementation • NeurIPS 2019 • Magauiya Zhussip, Shakarim Soltanayev, Se Young Chun
Here, we propose an extended SURE (eSURE) to train deep denoisers with correlated pairs of noise realizations per image and applied it to the case with two uncorrelated realizations per image to achieve better performance than SURE based method and comparable results to Noise2Noise.
no code implementations • 19 Dec 2018 • Dongwon Park, Yonghyeok Seo, Se Young Chun
However, rotation-invariance in robotic grasp detection has been only recently studied by using rotation anchor box that are often time-consuming and unreliable for multiple objects.
no code implementations • 18 Dec 2018 • Kwanyoung Kim, Se Young Chun
Recently, SRGAN was proposed to avoid this average effect by minimizing perceptual losses instead of l1 loss and it yielded perceptually better SR images (or images with sharp edges) at the price of lowering PSNR.
no code implementations • 16 Sep 2018 • Dongwon Park, Yonghyeok Seo, Se Young Chun
Our methods also achieved state-of-the-art detection accuracy (up to 96. 6%) with state-of- the-art real-time computation time for high-resolution images (6-20ms per 360x360 image) on Cornell dataset.
no code implementations • CVPR 2019 • Magauiya Zhussip, Shakarim Soltanayev, Se Young Chun
Our proposed methods were able to train deep learning based image denoisers from undersampled measurements without ground truth images and without image priors, and to recover images with state-of-the-art qualities from undersampled data.
3 code implementations • NeurIPS 2018 • Shakarim Soltanayev, Se Young Chun
Our quick refining method outperformed conventional BM3D, deep image prior, and often the networks trained with ground truth.
no code implementations • 4 Mar 2018 • Dongwon Park, Se Young Chun
Typically, regression based grasp detection methods have outperformed classification based detection methods in computation complexity with excellent accuracy.