no code implementations • 4 Apr 2024 • Jeongmin Bae, Seoha Kim, Youngsik Yun, Hahyun Lee, Gun Bang, Youngjung Uh
We attribute the failure to the wrong design of the deformation field, which is built as a coordinate-based function.
no code implementations • NeurIPS 2023 • JungWoo Chae, Hyunin Cho, Sooyeon Go, Kyungmook Choi, Youngjung Uh
The feature rearranger learns to rearrange original feature maps to match the shape of the proxy masks that are either from the original sample itself or from random samples.
1 code implementation • 20 Feb 2024 • Jaeseok Jeong, Junho Kim, Yunjey Choi, Gayoung Lee, Youngjung Uh
Despite their remarkable capability, existing models still face challenges in achieving controlled generation with a consistent style, requiring costly fine-tuning or often inadequately transferring the visual elements due to content leakage.
1 code implementation • 26 Oct 2023 • Dongkyun Kim, Mingi Kwon, Youngjung Uh
In this context, we propose a new evaluation protocol that measures the divergence of a set of generated images from the training set regarding the distribution of attribute strengths as follows.
1 code implementation • 20 Oct 2023 • Seoha Kim, Jeongmin Bae, Youngsik Yun, Hahyun Lee, Gun Bang, Youngjung Uh
Recent advancements in 4D scene reconstruction using neural radiance fields (NeRF) have demonstrated the ability to represent dynamic scenes from multi-view videos.
no code implementations • 2 Oct 2023 • Sangyun Lee, Gayoung Lee, Hyunsu Kim, Junho Kim, Youngjung Uh
We present the Groupwise Diffusion Model (GDM), which divides data into multiple groups and diffuses one group at one time interval in the forward diffusion process.
no code implementations • 25 Sep 2023 • Cheolhyun Mun, Sanghuk Lee, Youngjung Uh, Junsuk Choe, Hyeran Byun
Weakly-supervised semantic segmentation (WSSS) performs pixel-wise classification given only image-level labels for training.
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
1 code implementation • ICCV 2023 • Kibeom Hong, Seogkyu Jeon, Junsoo Lee, Namhyuk Ahn, Kunhee Kim, Pilhyeon Lee, Daesik Kim, Youngjung Uh, Hyeran Byun
To deliver the artistic expression of the target style, recent studies exploit the attention mechanism owing to its ability to map the local patches of the style image to the corresponding patches of the content image.
no code implementations • 27 Mar 2023 • Jaeseok Jeong, Mingi Kwon, Youngjung Uh
Instead, our method manipulates intermediate features within a feed-forward generative process.
no code implementations • 24 Feb 2023 • Yong-Hyun Park, Mingi Kwon, Junghyo Jo, Youngjung Uh
Despite the success of diffusion models (DMs), we still lack a thorough understanding of their latent space.
no code implementations • ICCV 2023 • Minjung Shin, Yunji Seo, Jeongmin Bae, Young Sun Choi, Hyunsu Kim, Hyeran Byun, Youngjung Uh
To solve this problem, we propose to approximate the background as a spherical surface and represent a scene as a union of the foreground placed in the sphere and the thin spherical background.
1 code implementation • 20 Oct 2022 • Mingi Kwon, Jaeseok Jeong, Youngjung Uh
To address the problem, we propose asymmetric reverse process (Asyrp) which discovers the semantic latent space in frozen pretrained diffusion models.
1 code implementation • CVPR 2023 • JiHye Park, Sunwoo Kim, Soohyun Kim, Seokju Cho, Jaejun Yoo, Youngjung Uh, Seungryong Kim
Existing techniques for image-to-image translation commonly have suffered from two critical problems: heavy reliance on per-sample domain annotation and/or inability of handling multiple attributes per image.
no code implementations • 22 Aug 2022 • Jeongmin Bae, Mingi Kwon, Youngjung Uh
Foreground-aware image synthesis aims to generate images as well as their foreground masks.
1 code implementation • CVPR 2022 • Junho Kim, Yunjey Choi, Youngjung Uh
In generative adversarial networks, improving discriminators is one of the key components for generation performance.
1 code implementation • CVPR 2021 • Hyunsu Kim, Yunjey Choi, Junho Kim, Sungjoo Yoo, Youngjung Uh
Although manipulating the latent vectors controls the synthesized outputs, editing real images with GANs suffers from i) time-consuming optimization for projecting real images to the latent vectors, ii) or inaccurate embedding through an encoder.
no code implementations • 11 Jan 2021 • Kibeom Hong, Youngjung Uh, Hyeran Byun
Training GANs on videos is even more sophisticated than on images because videos have a distinguished dimension: time.
no code implementations • ICCV 2021 • Minsong Ki, Youngjung Uh, Junsuk Choe, Hyeran Byun
The goal of unsupervised co-localization is to locate the object in a scene under the assumptions that 1) the dataset consists of only one superclass, e. g., birds, and 2) there are no human-annotated labels in the dataset.
no code implementations • 1 Jan 2021 • Hyunsu Kim, Yunjey Choi, Junho Kim, Sungjoo Yoo, Youngjung Uh
State-of-the-art GAN-based methods for editing real images suffer from time-consuming operations in projecting real images to latent vectors.
1 code implementation • 25 Sep 2020 • Minsong Ki, Youngjung Uh, Wonyoung Lee, Hyeran Byun
Furthermore, we propose foreground consistency loss that penalizes earlier layers producing noisy attention regarding the later layer as a reference to provide them with a sense of backgroundness.
4 code implementations • ICLR 2021 • Byeongho Heo, Sanghyuk Chun, Seong Joon Oh, Dongyoon Han, Sangdoo Yun, Gyuwan Kim, Youngjung Uh, Jung-Woo Ha
Because of the scale invariance, this modification only alters the effective step sizes without changing the effective update directions, thus enjoying the original convergence properties of GD optimizers.
1 code implementation • ICCV 2021 • Kyungjune Baek, Yunjey Choi, Youngjung Uh, Jaejun Yoo, Hyunjung Shim
To this end, we propose a truly unsupervised image-to-image translation model (TUNIT) that simultaneously learns to separate image domains and translates input images into the estimated domains.
3 code implementations • ICML 2020 • Muhammad Ferjad Naeem, Seong Joon Oh, Youngjung Uh, Yunjey Choi, Jaejun Yoo
In this paper, we show that even the latest version of the precision and recall metrics are not reliable yet.
14 code implementations • CVPR 2020 • Yunjey Choi, Youngjung Uh, Jaejun Yoo, Jung-Woo Ha
A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains.
Fundus to Angiography Generation Multimodal Unsupervised Image-To-Image Translation +1
2 code implementations • 22 Nov 2019 • Pilhyeon Lee, Youngjung Uh, Hyeran Byun
This formulation does not fully model the problem in that background frames are forced to be misclassified as action classes to predict video-level labels accurately.
Ranked #9 on Weakly Supervised Action Localization on ActivityNet-1.2 (mAP@0.5 metric)
Weakly Supervised Action Localization Weakly-supervised Temporal Action Localization +1
4 code implementations • ICCV 2019 • Jaejun Yoo, Youngjung Uh, Sanghyuk Chun, Byeongkyu Kang, Jung-Woo Ha
The key ingredient of our method is wavelet transforms that naturally fits in deep networks.