Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- C.‐C. Jay KuoSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works310 from public data
- Enhanced Deep Residual Networks for Single Image Super-Resolution7,719
This paper develops an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods, and proposes a new multi-scale deepsuper-resolution system (MDSR) and training method, which can reconstruct high-resolution images of different upscaling factors in a single model.
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks7,565
This work presents a highly accurate single-image superresolution (SR) method using a very deep convolutional network inspired by VGG-net used for ImageNet classification and uses extremely high learning rates enabled by adjustable gradient clipping.
- Deeply-Recursive Convolutional Network for Image Super-Resolution3,021
This work proposes an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN) with two extensions: recursive-supervision and skip-connection, which outperforms previous methods by a large margin.
- Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring2,588
This work proposes a multi-scale convolutional neural network that restores sharp images in an end-to-end manner where blur is caused by various sources and presents a new large-scale dataset that provides pairs of realistic blurry image and the corresponding ground truth sharp image that are obtained by a high-speed camera.
- 1,955
- 1,264
- 646
- Part-Aligned Bilinear Representations for Person Re-identification557
A novel network that learns a part-aligned representation for person re-identification that handles the body part misalignment problem, that is, body parts are misaligned across human detections due to pose/viewpoint change and unreliable detection.
- Reweighted Random Walks for Graph Matching545
This work proposes a robust graph matching algorithm against outliers and deformation by simulating random walks with reweighting jumps enforcing the matching constraints on the association graph and achieves noise-robust graph matching by iteratively updating and exploiting the confidences of candidate correspondences.
- I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image518
The proposed I2L-MeshNet predicts the per-lixel likelihood on 1D heatmaps for each mesh vertex coordinate instead of directly regressing the parameters, and preserves the spatial relationship in the input image and models the prediction uncertainty.
- Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose488
Pose2Mesh is a novel graph convolutional neural network (GraphCNN)-based system that estimates the 3D coordinates of human mesh vertices directly from the 2D human pose, which avoids the representation issues, while fully exploiting the mesh topology using a GraphCNN in a coarse-to-fine manner.
- V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map473
This model is designed as a 3D CNN that provides accurate estimates while running in real-time and outperforms previous methods in almost all publicly available 3D hand and human pose estimation datasets and placed first in the HANDS 2017 frame-based3D hand pose estimation challenge.
- 445
- InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image427
A large-scale dataset, InterHand2.6M, and a baseline network, InterNet, for 3D interacting hand pose estimation from a single RGB image, which serves as a strong baseline for this new dataset.
- Camera Distance-Aware Top-Down Approach for 3D Multi-Person Pose Estimation From a Single RGB Image382
This work firstly proposes a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image, which achieves comparable results with the state-of-the-art 3D single- person pose estimation models without any groundtruth information and significantly outperforms previous 3DMulti-Person pose estimation methods on publicly available datasets.
- Channel Attention Is All You Need for Video Frame Interpolation381
A simple but effective deep neural network for video frame interpolation, which is end-to-end trainable and is free from a motion estimation network component, and achieves outstanding performance compared to the existing models with a component for optical flow computation.
- 314
- Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video303
This work presents a temporally consistent mesh recovery system (TCMR) that effectively focuses on the past and future frames’ temporal information without being dominated by the current static feature of the current frame.
- Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images281
This paper regularizes the optimization process of 3D Gaussian splatting with the adjusted depth and an additional unsupervised smooth constraint, thereby effectively reducing the occurrence of floating artifacts.
- Deep vessel segmentation by learning graphical connectivity253
Comparisons are performed on four retinal image datasets and a coronary artery X-ray angiography dataset, showing that the proposed method outperforms or is on par with current state-of-the-art methods in terms of the average precision and the area under the receiver operating characteristic curve.
- 239
- AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network224
This work develops AP-BSN, a state-of-the-art self-supervised denoising method for real-world sRGB images, and proposes random-replacing refinement, which significantly improves the performance of the AP- BSN without any additional parameters.
- 217
- 208
- 196
- 193
- 188
- PoseFix: Model-Agnostic General Human Pose Refinement Network186
This paper proposes a human pose refinement network that estimates a refined pose from a tuple of an input image and input pose and shows that the proposed approach achieves better performance than the conventional multi-stage refinement models and consistently improves the performance of various state-of-the-art pose estimation methods on the commonly used benchmark.
- HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network183
This work proposes a novel 3D hand mesh estimation network HandOccNet, that can fully exploits the information at occluded regions as a secondary means to enhance image features and make it much richer.
- Generalized video deblurring for dynamic scenes183
This work proposes a single energy model that simultaneously estimates optical flows and latent frames to solve the deblurring problem and achieves significant improvements in removing blurs and estimating accurate optical flows in blurry frames.
- Online Video Deblurring via Dynamic Temporal Blending Network181
An online (sequential) video deblurring method based on a spatio-temporal recurrent network that allows for realtime performance and introduces a novel architecture which extends the receptive field while keeping the overall size of the network small to enable fast execution.
- 177
- 172
- Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning161
This work introduces a new meta-learning framework with a loss function that adapts to each task, named Meta-Learning with Task-Adaptive Loss Function (MeTAL), which demonstrates the effectiveness and the flexibility across various domains, such as few-shot classification and few- shot regression.
- Generative Image Segmentation Using Random Walks with Restart161
A new generative image segmentation algorithm for reliable multi-label segmentations in natural images that produces very good segmentation results under two difficult problems: the weak boundary problem and the texture problem.
- 155
- 152
- 148
- 145
- Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation140
This work designs Pose2Pose, a module that utilizes joint features for 3D joint rotations in the human kinematic chain and presents Hand4Whole, which has two strong points over previous works.
- 136
- Ghost-Free High Dynamic Range Imaging130
This paper proposes a new robust ghost-free HDRI generation algorithm that does not require accurate ghost detection and not suffer from the color artifact problem, and utilizes the global intensity transfer functions obtained from joint probability density functions between different exposure images.
- CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Image125
This work proposes a novel and powerful self-supervised denoising method called CVF-SID based on a Cyclic multi-Variate Function (CVF) module and a self- supervised image disentangling (SID) framework, which can disentangle a clean image and noise maps from the input by leveraging various self- Supervised loss terms.
- Learning to Forget for Meta-Learning114
This work proposes task-and-layer-wise attenuation on the compromised initialization of model-agnostic meta-learning to reduce its influence and names the method as L2F (Learn to Forget).
- Occlusion invariant face recognition using selective local non-negative matrix factorization basis images114
The experimental results demonstrate that the proposed local patch-based occlusion detection technique works well and the S-LNMF method shows superior performance to other conventional approaches.
- Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes113
3DCrowdNet is presented that firstly explicitly targets in-the-wild crowded scenes and estimates a robust 3D human mesh by addressing the above issues and proposes a joint-based regressor that distinguishes a target person's feature from others.
- 109
- NTIRE 2021 Challenge on Image Deblurring106
The winning methods demonstrate the state-of-the-art performance on the image deblurring task with the jointly combined artifacts.
- Look Wider to Match Image Patches With Convolutional Neural Networks106
A novel convolutional neural network module to learn a stereo matching cost with a large-sized window that can successfully utilize the information from a large area without introducing the fattening effect is proposed.
- Fusion of Lidar and Imagery for Reliable Building Extraction104
A new building detection and description algorithm for lidar data and photogrammetric imagery is proposed using directional histograms, splitting and merging segments, and line segments matching to extract precise building boundaries.
- Shape from Shading with a Generalized Reflectance Map Model103
This research derives a physics-based generalized reflectance map model which includes diffuse and specular reflection effects, a nearby point light source and perspective projection, and then develops a new direct shape recovery algorithm from shaded images which linearizes the nonlinear equations and minimizing a quadratic cost functional.
- 98
- Task-Aware Image Downscaling96
This paper proposes an auto-encoder-based framework that enables joint learning of the downscaling network and the upsc scaling network to maximize the restoration performance and validates the model’s generalization capability by applying it to the task of image colorization.
- Clustering Convolutional Kernels to Compress Deep Neural Networks89
A novel method to compress CNNs by reconstructing the network from a small set of spatial convolution kernels using k-means clustering, which outperforms its uncompressed counterpart at ILSVRC2012 classification task with over 10x compression ratio.
- Tracking of Abrupt Motion Using Wang-Landau Monte Carlo Estimation88
A novel tracking algorithm based on the Wang-Landau Monte Carlo sampling method which efficiently deals with the abrupt motions and efficiently samples the object's states even in a whole state space without loss of time is proposed.
- NeuralAnnot: Neural Annotator for 3D Human Mesh Training Sets87
3D pseudo-GTs of NeuralAnnot, a neural network-based annotator, are shown to be highly beneficial to train the regressors of 3D human mesh regressors.
- 87
- 85
- 81
- SPNet: Deep 3D Object Classification and Retrieval Using Stereographic Projection80
An efficient Stereographic Projection Neural Network (SPNet) for learning representations of 3D objects that performs comparably to the state-of-the-art methods while having substantially lower GPU memory as well as network parameters is proposed.
- 76
- Recognition of 2D Object Contours Using Starting-Point-Independent Wavelet Coefficient Matching75
A new recognition algorithm for 2D object contours, based on the decimated wavelet transform, is presented, emphasizing the starting point dependency problem, and requires only less than 25% of the computational load required for the conventional method.
- DeepHandMesh: A Weakly-Supervised Deep Encoder-Decoder Framework for High-Fidelity Hand Mesh Modeling72
The proposed DeepHandMesh is a weakly-supervised deep encoder-decoder framework for high-fidelity hand mesh modeling that provides significantly more realistic hand mesh than previous fully- supervised hand models.
- Co-recognition of Image Pairs by Data-Driven Monte Carlo Image Exploration70
Generative model for co-recognition for object-level image matching between an arbitrary image pair is presented and data-driven Monte Carlo image exploration which clusters and propagates local region matches by Markov chain dynamics is proposed.
- Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report69
The target is to develop an end-to-end deep learning-based video super-resolution solutions that can achieve a realtime performance on mobile GPUs and can upscale videos to HD resolution at up to 80 FPS while demonstrating high fidelity results.
- 68
- 65
- 65
- 64
- Joint segmentation and classification of hepatic lesions in ultrasound images using deep learning63
The joint segmentation and classification system could assist radiologists with minimal experience in US imaging by characterizing hepatic lesions and exhibited higher performance than segmentation only and classification only systems.
- 62
- 60
- 59
- 58
- 58
- 58
- 58
- Real-time visual tracking by deep reinforced decision making56
This paper introduces a novel real-time visual tracking algorithm based on a template selection strategy constructed by deep reinforcement learning methods that is generally applicable to other confidence map based tracking algorithms.
- Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution from a Blurred Image Sequence56
This paper proposes a pioneering unified framework that solves four problems simultaneously, namely, dense depth reconstruction, camera pose estimation, super-resolution, and deblurring, by reflecting a physical imaging process and solving the cost minimization problem using an alternating optimization technique.
- Tracking by Sampling and IntegratingMultiple Trackers56
The visual tracker sampler is proposed, a novel tracking algorithm that can work robustly in challenging scenarios, where several kinds of appearance and motion changes of an object can occur simultaneously, and outperforms even state-of-the-art tracking methods.
- DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks55
This work introduces a new ultra-low precision yet effective quantization approach specifically designed for SR, dubbed Distribution-Aware Quantization (DAQ), which manages to greatly reduce the computational and resource costs without the significant sacrifice in SR performance, compared to other quantization methods.
- ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Images53
This work presents ExBluRF, a novel view synthesis method for extreme motion blurred images based on efficient radiance fields optimization that restores much sharper 3D scenes from challenging motion blurred views with the order of 10× less training time and GPU memory consumption.
- 53
- Surface reconstruction from photometric stereo images52
An explicit surface model based on nodal basis-function representation is used so that the integrability problem that arises in conventional photometric stereo SFS algorithms can be solved easily.
- Scene-Adaptive Video Frame Interpolation via Meta-Learning50
This work shows the benefits of 'test-time adaptation' through simple fine-tuning of a network, then improves its efficiency by incorporating meta-learning, and obtains significant performance gains with only a single gradient update without any additional parameters.
- Continual Learning by Asymmetric Loss Approximation With Single-Side Overestimation49
This work proposes a novel approach to continual learning by approximating a true loss function using an asymmetric quadratic function with one of its sides overestimated, which achieves the state-of-the-art accuracy that is even close to the upper-bound performance on several challenging benchmark datasets.
- 49
- SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation48
This work interprets the traditional image warping task, specifically when the input is enlarged, as a spatially-varying SR problem and proposes several novel formulations, including the adaptive warping layer and multiscale blending, to reconstruct visually favorable results in the transformation process.
- Toward Real-World Super-Resolution via Adaptive Downsampling Models48
This study proposes a novel method to simulate an unknown downsampling process without imposing restrictive prior knowledge and proposes a generalizable low-frequency loss (LFL) in the adversarial training framework to imitate the distribution of target LR images without using any paired examples.
- 46
- Recognition of partially occluded objects using probabilistic ARG (attributed relational graph)-based matching46
Experimental results on real images demonstrate that the proposed algorithm has superior performance to those of the conventional relaxation algorithms, by localizing target objects robustly and correctly even in severely noisy and occluded scenes.
- 45
- Graph Matching via Sequential Monte Carlo44
A novel approach to graph matching is developed based on the sequential Monte Carlo framework by constructing a sequence of intermediate target distributions and sequentially performs a sampling and importance resampling to maximize the graph matching objective.
- 44
- 44
- Bilateral Symmetry Detection via Symmetry-Growing42
A novel and robust method for localizing and segmenting bilaterally symmetric patterns from real-world images that overcomes the limitations of the previous local-feature based approaches by efciently exploring the image space to grow symmetry beyond the detected symmetric features.
- 41
- 41
- 39
- 38
- 38
- IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos37
The main idea is to let the pose stream decide how much and which appearance information is used in integration based on whether the given pose information is reliable or not, and show that the proposed IntegralAction achieves highly robust performance across in-context and out-of-context action video datasets.
- 37
- Color-Based Image Retrieval Using Perceptually Modified Hausdorff Distance37
This paper extracts the perceptual representation of an original color image, a statistical signature by modifying general color signature, which consists of a set of points with statistical volume, and presents a novel dissimilarity measure for a statistical signatures called Perceptually Modified Hausdorff Distance (PMHD) that is based on the Hhausdorff distance.
- 37
- NTIRE 2021 Challenge on Video Super-Resolution36
This paper presents evaluation results from two competition tracks as well as the proposed solutions to the NTIRE 2021 Challenge on Video Super-Resolution, and develops conventional video SR methods focusing on the restoration quality.
- NTIRE 2020 Challenge on Image and Video Deblurring35
This challenge presents the evaluation results from 3 competition tracks as well as the proposed solutions, and the winning methods demonstrate the state-of-the-art performance on image and video deblurring tasks.
- 35
- 34
- DynaVSR: Dynamic Adaptive Blind Video Super-Resolution32
DynaVSR is presented, a novel meta-learning-based framework for real-world video SR that enables efficient downscaling model estimation and adaptation to the current input and consistently improves the performance of the state-of-the-art video SR models by a large margin.
- 32
- A deep learning-based framework for retinal fundus image enhancement30
An automatic fundus macular image enhancement framework that automatically enhances low-quality retinal fundus images that suffer from complex degradation and achieves improved performance over the existing state-of-the-art methods is proposed.
- 29
- 29
- 27
- 27
- 25
- 25
- 24
- 24
- 24
- 23
- 23
- 23
- 22
- AIM 2020 Challenge on Video Temporal Super-Resolution22
This paper reports the second AIM challenge on Video Temporal Super-Resolution (VTSR), a.k.a. frame interpolation, with a focus on the proposed solutions, results, and analysis, and proposes the enhanced quadratic video interpolation method.
- 22
- 22
- 21
- 21
- 20
- AIM 2019 Challenge on Video Temporal Super-Resolution: Methods and Results20
This paper reviews the first AIM challenge on video temporal super-resolution (frame interpolation) with a focus on the proposed solutions and results, and employs the REDS_VTSR dataset derived from diverse videos captured in a hand-held camera for training and evaluation purposes.
- 20
- 20
- 20
- 19
- 19
- 19
- 18
- 18
- 18
- 17
- 17
- 16
- 16
- 16
- 16
- 16
- 15
- 15
- 15
- 15
- 14
- 14
- 14
- 14
- 14
- 13
- 13
- 13
- 13
- 13
- 12
- 12
- 12
- 12
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- 10
- 10
- 9
- Geometric particle swarm optimization for robust visual ego-motion estimation via particle filtering9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.