14 citations · 25 across the 12 of their papers we have counts for
12 papers
Language-Assisted Super-Resolution from Real-World Low-Resolution Patches
Joonkyu Park, Kyoung Mu Lee
Single image super-resolution aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs. Training SR models typically requires paired HR-LR data, which is dif…
MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook
Peng Xu, Shengwu Xiong, Jiajun Zhang +125
This paper reviews the MARS2 2025 Challenge on Multimodal Reasoning. We aim to bring together different approaches in multimodal machine learning and LLMs via a large benchmark. We…
GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring
Dongwoo Lee, Joonkyu Park, Kyoung Mu Lee
To train a deblurring network, an appropriate dataset with paired blurry and sharp images is essential. Existing datasets collect blurry images either synthetically by aggregating…
Rethinking RGB Color Representation for Image Restoration Models
Jaerin Lee, JoonKyu Park, Sungyong Baik +1
Image restoration models are typically trained with a pixel-wise distance loss defined over the RGB color representation space, which is well known to be a source of blurry and unr…
Extract-and-Adaptation Network for 3D Interacting Hand Mesh Recovery
JoonKyu Park, Daniel Sungho Jung, Gyeongsik Moon +1
Understanding how two hands interact with each other is a key component of accurate 3D interacting hand mesh recovery. However, recent Transformer-based methods struggle to learn t…
Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding
Yeonguk Oh, JoonKyu Park, Jaeha Kim +2
Hands, one of the most dynamic parts of our body, suffer from blur due to their active movements. However, previous 3D hand mesh recovery methods have mainly focused on sharp hand…
Pay Attention to Hidden States for Video Deblurring: Ping-Pong Recurrent Neural Networks and Selective Non-Local Attention
JoonKyu Park, Seungjun Nah, Kyoung Mu Lee
Video deblurring models exploit information in the neighboring frames to remove blur caused by the motion of the camera and the objects. Recurrent Neural Networks~(RNNs) are often…
HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network
JoonKyu Park, Yeonguk Oh, Gyeongsik Moon +2
Hands are often severely occluded by objects, which makes 3D hand mesh estimation challenging. Previous works often have disregarded information at occluded regions. However, we ar…
Recurrence-in-Recurrence Networks for Video Deblurring
Joonkyu Park, Seungjun Nah, Kyoung Mu Lee
State-of-the-art video deblurring methods often adopt recurrent neural networks to model the temporal dependency between the frames. While the hidden states play key role in delive…
Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes
Hongsuk Choi, Gyeongsik Moon, JoonKyu Park +1
We consider the problem of recovering a single person's 3D human mesh from in-the-wild crowded scenes. While much progress has been in 3D human mesh estimation, existing methods st…
Generative Adversarial Networks for Unsupervised Object Co-localization
Junsuk Choe, Joo Hyun Park, Hyunjung Shim
This paper introduces a novel approach for unsupervised object co-localization using Generative Adversarial Networks (GANs). GAN is a powerful tool that can implicitly learn unknow…
Improved Techniques For Weakly-Supervised Object Localization
Junsuk Choe, Joo Hyun Park, Hyunjung Shim
We propose an improved technique for weakly-supervised object localization. Conventional methods have a limitation that they focus only on most discriminative parts of the target o…