Kyoung Mu Lee

56

Papers

497

Total Citations

Papers (56)

Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose

Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer

CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning

CNC-Net: Self-Supervised Learning for CNC Machining Operations

MRF Optimization by Graph Approximation

SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models

Exploiting Diffusion Prior for Task-driven Image Restoration

OmniSplat: Taming Feed-Forward 3D Gaussian Splatting for Omnidirectional Images with Editable Capabilities

Deeply-Recursive Convolutional Network for Image Super-Resolution

Accurate Image Super-Resolution Using Very Deep Convolutional Networks

Deep Multi-Scale Convolutional Neural Network for Dynamic Scene Deblurring

SeedNet: Automatic Seed Generation With Deep Reinforcement Learning for Robust Interactive Segmentation

Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals

V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation From a Single Depth Map

Stochastic Class-Based Hard Example Mining for Deep Metric Learning

PoseFix: Model-Agnostic General Human Pose Refinement Network

Recurrent Neural Networks With Intra-Frame Iterations for Video Deblurring

Learning to Forget for Meta-Learning

Scene-Adaptive Video Frame Interpolation via Meta-Learning

Beyond Static Features for Temporally Consistent 3D Human Pose and Shape From a Video

SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation

CVF-SID: Cyclic Multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise From Image

HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network

AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network

Attentive Fine-Grained Structured Sparsity for Image Restoration

Learning To Estimate Robust 3D Human Mesh From In-the-Wild Crowded Scenes

Recovering 3D Hand Mesh Sequence From a Single Blurry Image: A New Dataset and Temporal Unfolding

ACL-SPC: Adaptive Closed-Loop System for Self-Supervised Point Cloud Completion

Discrete Tabu Search for Graph Matching

Online Video Deblurring via Dynamic Temporal Blending Network

Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution From a Blurred Image Sequence

Deep Meta Learning for Real-Time Target-Aware Visual Tracking

Continual Learning by Asymmetric Loss Approximation With Single-Side Overestimation

Camera Distance-Aware Top-Down Approach for 3D Multi-Person Pose Estimation From a Single RGB Image

C2N: Practical Generative Noise Modeling for Real-World Denoising

Meta-Learning With Task-Adaptive Loss Function for Few-Shot Learning

3DIAS: 3D Shape Reconstruction With Implicit Algebraic Surfaces

Searching for Controllable Image Restoration Networks

Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction

Content-Aware Local GAN for Photo-Realistic Super-Resolution

Human Part-wise 3D Motion Context Learning for Sign Language Recognition

ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Images

DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling

I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image

InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image

3D Clothed Human Reconstruction in the Wild

CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution

Motion-Aware Dynamic Architecture for Efficient Frame Interpolation

DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image

PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Image

Auto-Regressive Transformation for Image Alignment

Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss

AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution

Subgraph Matching Using Compactness Prior for Robust Feature Correspondence

Generalized Video Deblurring for Dynamic Scenes

Meta-Learning with Adaptive Hyperparameters