255 citations · 855 across the 35 of their papers we have counts for
47 papers
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…
ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Images
Dongwoo Lee, Jeongtaek Oh, Jaesung Rim +2
We present ExBluRF, a novel view synthesis method for extreme motion blurred images based on efficient radiance fields optimization. Our approach consists of two main components: 6…
Extraction of Coronary Vessels in Fluoroscopic X-Ray Sequences Using Vessel Correspondence Optimization
Seung Yeon Shin, Soochahn Lee, Kyoung Jin Noh +2
We present a method to extract coronary vessels from fluoroscopic x-ray sequences. Given the vessel structure for the source frame, vessel correspondence candidates in the subseque…
Searching for Controllable Image Restoration Networks
Heewon Kim, Sungyong Baik, Myungsub Choi +2
Diverse user preferences over images have recently led to a great amount of interest in controlling the imagery effects for image restoration tasks. However, existing methods requi…
Meta-Learning with Adaptive Hyperparameters
Sungyong Baik, Myungsub Choi, Janghoon Choi +2
Despite its popularity, several recent works question the effectiveness of MAML when test tasks are different from training tasks, thus suggesting various task-conditioned methodol…
DynaVSR: Dynamic Adaptive Blind Video Super-Resolution
Suyoung Lee, Myungsub Choi, Kyoung Mu Lee
Most conventional supervised super-resolution (SR) algorithms assume that low-resolution (LR) data is obtained by downscaling high-resolution (HR) data with a fixed known kernel, b…
Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video
Hongsuk Choi, Gyeongsik Moon, Ju Yong Chang +1
Despite the recent success of single image-based 3D human pose and shape estimation methods, recovering temporally consistent and smooth 3D human motion from a video is still chall…
AIM 2020 Challenge on Video Temporal Super-Resolution
Sanghyun Son, Jaerin Lee, Seungjun Nah +2
Videos in the real-world contain various dynamics and motions that may look unnaturally discontinuous in time when the recordedframe rate is low. This paper reports the second AIM…
Domain Adaptation of Learned Features for Visual Localization
Sungyong Baik, Hyo Jin Kim, Tianwei Shen +3
We tackle the problem of visual localization under changing conditions, such as time of day, weather, and seasons. Recent learned local features based on deep neural networks have…
InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image
Gyeongsik Moon, Shoou-i Yu, He Wen +2
Analysis of hand-hand interactions is a crucial step towards better understanding human behavior. However, most researches in 3D hand pose estimation have focused on the isolated s…
DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling
Gyeongsik Moon, Takaaki Shiratori, Kyoung Mu Lee
Human hands play a central role in interacting with other people and objects. For realistic replication of such hand motions, high-fidelity hand meshes have to be reconstructed. In…
A Spectrometric Approach to Measuring the Rayleigh Scattering Length for Liquid Scintillator Detectors
S. S. Gokhale, R. Rosero, R. Diaz Perez +3
Good optical transparency is a fundamental requirement of liquid scintillator (LS) detectors. Characterizing the transparency of a liquid scintillator to its own emitted light is a…
I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image
Gyeongsik Moon, Kyoung Mu Lee
Most of the previous image-based 3D human pose and mesh estimation methods estimate parameters of the human mesh model from an input image. However, directly regressing the paramet…
Visual Tracking by TridentAlign and Context Embedding
Janghoon Choi, Junseok Kwon, Kyoung Mu Lee
Recent advances in Siamese network-based visual tracking methods have enabled high performance on numerous tracking benchmarks. However, extensive scale variations of the target ob…
IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos
Gyeongsik Moon, Heeseung Kwon, Kyoung Mu Lee +1
Most current action recognition methods heavily rely on appearance information by taking an RGB sequence of entire image regions as input. While being effective in exploiting conte…
NTIRE 2020 Challenge on Image and Video Deblurring
Seungjun Nah, Sanghyun Son, Radu Timofte +1
Motion blur is one of the most common degradation artifacts in dynamic scene photography. This paper reviews the NTIRE 2020 Challenge on Image and Video Deblurring. In this challen…
AIM 2019 Challenge on Video Temporal Super-Resolution: Methods and Results
Seungjun Nah, Sanghyun Son, Radu Timofte +1
Videos contain various types and strengths of motions that may look unnaturally discontinuous in time when the recorded frame rate is low. This paper reviews the first AIM challeng…
Scene-Adaptive Video Frame Interpolation via Meta-Learning
Myungsub Choi, Janghoon Choi, Sungyong Baik +2
Video frame interpolation is a challenging problem because there are different scenarios for each video depending on the variety of foreground and background motion, frame rate, an…
Fine-Grained Neural Architecture Search
Heewon Kim, Seokil Hong, Bohyung Han +2
We present an elegant framework of fine-grained neural architecture search (FGNAS), which allows to employ multiple heterogeneous operations within a single layer and can even gene…
PoseLifter: Absolute 3D human pose lifting network from a single noisy 2D human pose
Ju Yong Chang, Gyeongsik Moon, Kyoung Mu Lee
This study presents a new network (i.e., PoseLifter) that can lift a 2D human pose to an absolute 3D pose in a camera coordinate system. The proposed network estimates the absolute…
Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image
Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee
Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly prop…
Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation
Dongmin Park, Seokil Hong, Bohyung Han +1
Catastrophic forgetting is a critical challenge in training deep neural networks. Although continual learning has been investigated as a countermeasure to the problem, it often suf…
Learning to Forget for Meta-Learning
Sungyong Baik, Seokil Hong, Kyoung Mu Lee
Few-shot learning is a challenging problem where the goal is to achieve generalization from only few examples. Model-agnostic meta-learning (MAML) tackles the problem by formulatin…
Multi-scale Aggregation R-CNN for 2D Multi-person Pose Estimation
Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee
Multi-person pose estimation from a 2D image is challenging because it requires not only keypoint localization but also human detection. In state-of-the-art top-down methods, multi…