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
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works115 from public data
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks4,943
This work thoroughly study three key components of SRGAN – network architecture, adversarial loss and perceptual loss, and improves each of them to derive an Enhanced SRGAN (ESRGAN), which achieves consistently better visual quality with more realistic and natural textures than SRGAN.
- RankSRGAN: Generative Adversarial Networks With Ranker for Image Super-Resolution412
This work first train a Ranker which can learn the behavior of perceptual metrics and then introduce a novel rank-content loss to optimize the perceptual quality, and shows that RankSRGAN achieves visually pleasing results and reaches state-of-the-art performance in perceptual metrics.
- FD-GAN: Generative Adversarial Networks with Fusion-Discriminator for Single Image Dehazing332
A fully end-to-end Generative Adversarial Networks with Fusion-discriminator (FD-GAN) for image dehazing which takes frequency information as additional priors and can generator more natural and realistic dehazed images with less color distortion and fewer artifacts.
- Learn to Match: Automatic Matching Network Design for Visual Tracking256
This work introduces six novel matching operators from the perspective of feature fusion instead of explicit similarity learning, namely Concatenation, Pointwise-Addition, Pairwise-Relation, FiLM, Simple-Transformer and Transductive-Guidance, to explore more feasibility on matching operator selection.
- Blind Image Super-Resolution: A Survey and Beyond228
A taxonomy to categorize existing methods into three different classes according to their ways of degradation modelling and the data used to solve the SR model is proposed, which helps summarize and distinguish among existing methods.
- A Survey of Reinforcement Learning for Large Reasoning Models175
Research applying RL to LLMs and LRMs for reasoning abilities is examined, especially since the release of DeepSeek-R1, including foundational components, core problems, training resources, and downstream applications, to identify future opportunities and directions for this rapidly evolving area.
- Conditional Sequential Modulation for Efficient Global Image Retouching156
An extremely light-weight framework - Conditional Sequential Retouching Network (CSRNet) - for efficient global image retouching is proposed that achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively.
- Masked Image Training for Generalizable Deep Image Denoising143
This work presents a novel approach to enhance the generalization performance of denoising networks, known as masked training, which involves masking random pixels of the input image and reconstructing the missing information during training.
- HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization126
This work proposes a novel learning-based approach using a spatially dynamic encoder-decoder network, HDRUNet, to learn an end-to-end mapping for single image HDR reconstruction with denoising and dequantization, which achieves the state-of-the-art performance in quantitative comparisons and visual quality.
- Enhanced Quadratic Video Interpolation100
This work improves the performance of QVI from three facets and proposes an enhanced quadratic video interpolation (EQVI) model that won the first place in the AIM2020 Video Temporal Super-Resolution Challenge and devise a novel multi-scale fusion network (MS-Fusion) which can be regarded as a learnable augmentation process.
- Temporally consistent video colorization with deep feature propagation and self-regularization learning67
A novel temporally consistent video colorization (TCVC) framework that effectively propagates frame-level deep features in a bidirectional way to enhance the temporal consistency of colorization and introduces a self-regularization learning (SRL) scheme to minimize the differences in predictions obtained using different time steps.
- RankSRGAN: Super Resolution Generative Adversarial Networks With Learning to Rank64
This work first train a Ranker which can learn the behaviour of perceptual metrics and then introduces a novel rank-content loss to optimize the perceptual quality, and extends the method to multiple Rankers to provide multi-dimension constraints for the generator.
- 59
- SAMM (Segment Any Medical Model): A 3D Slicer Integration to SAM47
This work introduces Segment Any Medical Model (SAMM), an extension of SAM on 3D Slicer, an open-source extension to 3D Slicer extensively used by the medical imaging community.
- Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects47
The generalized object confidence (GOC) score is introduced, which only uses known samples for supervision and avoids improper suppression of unknowns in the back-ground and the Unknown Object Detection Benchmark is presented, the first publicly benchmark that encompasses precision evaluation for unknown detection to the authors' knowledge.
- Unifying Image Processing as Visual Prompting Question Answering44
Inspired by NLP question answering techniques, PromptGIP treats the input-output image pair as a structured question-answer sentence, thereby reprogramming the image processing task as a prompting QA problem, eliminating the need for task-specific finetuning.
- A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds44
This work proposes a unified gated degradation model to generate a broad set of degradation cases using a random gate controller and proposes simple baseline networks that can effectively handle non-blind, classical, practical degradation cases as well as many other corner cases.
- FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution42
Extensive experiments show that FlashVSR scales reliably to ultra-high resolutions and achieves state-of-the-art performance with up to 12x speedup over prior one-step diffusion VSR models.
- ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding40
ArtiMuse, an innovative MLLM-based IAA model with Joint Scoring and Expert-Level Understanding capabilities, and ArtiMuse-10K, the first expert-curated image aesthetic dataset, each annotated by professional experts with 8-dimensional attributes analysis and a holistic score are presented.
- 40
- MagHacker39
MagHacker is a new sensing system that realizes such eavesdropping attack over commodity mobile devices, which monitor and analyze the magnetic field being produced by the stylus pen's internal magnet.
- UDC 2020 Challenge on Image Restoration of Under-Display Camera: Methods and Results38
The results in the paper are state-of-the-art restoration performance of Under-Display Camera Restoration.
- 37
- Evaluating the Generalization Ability of Super-Resolution Networks34
This work makes the first attempt to propose a Generalization Assessment Index for Super-Resolution (SR) networks, namely SRGA, which exploits the statistical characteristics of the internal features of deep networks to measure the generalization ability.
- Very Lightweight Photo Retouching Network With Conditional Sequential Modulation34
An extremely lightweight framework – Conditional Sequential Retouching Network (CSRNet) that achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively and can be easily extended to learn local enhancement effects.
- 34
- 32
- A fine recognition method of strawberry ripeness combining Mask R-CNN and region segmentation29
The comprehensive results demonstrate that the proposed method enables the evaluation of six distinct ripeness levels of strawberries in the complex field environment and can provide accurate decision support for strawberry refined planting management.
- Microenvironment-responsive MOF nanozymes armored cryogels promoted wound healing via rapid hemostasis, infection elimination and angiogenesis27
A microenvironment-responsive multifunctional platinum-armed iron-based MOF nanocomposite (Pt@FeMOF) to repair chronic wounds and induces ferroptosis in bacteria via lipid peroxidation, GSH depletion, iron overload, and disruption of arginine metabolism.
- CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm27
Inspired by prompting approaches from NLP, this work creatively reinterpret point cloud generation and refinement as the prompting and predicting stages, respectively, and develops a novel Semantic Conditional Refinement (SCR) network at the predicting stage.
- Learning A Low-Level Vision Generalist via Visual Task Prompt24
A Visual task Prompt-based Image Processing (VPIP) framework is proposed, which employs visual task prompts to manage tasks with different input-target domains and allows flexible selection of backbone network suitable for general tasks.
- Learning to See Low-Light Images via Feature Domain Adaptation22
A single-stage network empowered by Feature Domain Adaptation (FDA) to decouple the denoising and color mapping tasks in raw LLIE achieves state-of-the-art performance with fewer computing costs (60% FLOPs of the two-stage method DNF).
- 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.
- 20
- 20
- Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis19
Experimental results on face and dance datasets show that TS-Net achieves better performance in video motion retargeting than several state-of-the-art models as well as its single-branch variants.
- PICABench: How Far Are We from Physically Realistic Image Editing?17
PICABench is introduced, which systematically evaluates physical realism across eight sub-dimension (spanning optics, mechanics, and state transitions) for most of the common editing operations (add, remove, attribute change, etc.), and the PICAEval is proposed, a reliable evaluation protocol that uses VLM-as-a-judge with per-case, region-level human annotations and questions.
- Factuality Matters: When Image Generation and Editing Meet Structured Visuals17
This work presents the first comprehensive, systematic investigation of structured visuals domain, encompassing data construction, model training, and an evaluation benchmark, and introduces StructBench, a novel benchmark for generation and editing with over 1,700 challenging instances.
- WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning16
This paper introduces the first generalist weather foundation model (WeatherGFM), designed to address a wide spectrum of weather understanding tasks in a unified manner and adopts a visual prompting question-answering paradigm for the training of unified weather understanding tasks.
- SuperRL: Reinforcement Learning with Supervision to Boost Language Model Reasoning15
This work introduces SuperRL, a unified training framework that adaptively alternates between RL and SFT and shows that SuperRL surpasses vanilla RL by delivering higher sample efficiency, stronger generalization, and improved robustness under sparse rewards.
- Multi-Agent Pickup and Delivery with Task Deadlines15
This work defines metrics to effectively determine which task is most worth assignment next and which agent ought to execute a given task, and proposes a priority-based framework for joint task assignment and path planning.
- Research of Under-Sampling Technique for Digital Image Correlation in Vibration Measurement14
A new testing method targeting at operating deflecting shape vibration test based on stereo vision is developed and a timestamp-based optimization method is proposed and developed to address Jitter problem in the process of undersampling.
- 13
- 13
- Bi-directional MS lesion filling and synthesis using denoising diffusion implicit model-based lesion repainting12
A novel approach leveraging Denoising Diffusion Implicit Models (DDIMs) for both MS lesion filling and synthesis based on image inpainting is proposed, which enables both MS lesion filing and synthesis of lesioned tissues.
- 12
- Label super resolution for 3D magnetic resonance images using deformable U-net12
A 3D label super resolution (LSR) method which does not use an external image or label from a HR atlas data and can reconstruct HR annotation labels only reliant on a LR image and corresponding label pairs is proposed.
- Multi-Agent Path Execution with Uncertainty11
This paper defines a feasibility problem to check whether the remaining portion of a path plan can be successfully executed and proposes a feasibility test algorithm, which is proved that the problem is NP-complete and proposed a feasibility test algorithm.
- 11
- 10
- 9
- GBEC: Geometry-Based Hand-Eye Calibration9
Geometry-Based End-Effector Calibration (GBEC) is proposed that enhances the repeatability and accuracy of the derived transformation compared to traditional hand-eye calibrations, making it independent of workspace constraints or robot accuracy, without sacrificing the orthogonality of the rotation matrix.
- 9
- The reduced cortical bone density in vertebral bodies: risk for osteoporotic fractures? Insights from CT analysis8
It is suggested that reduction in cortical BMD has a greater impact on OVCF than reduction in cancellous BMD, along with biomechanical factors.
- 8
- 8
- 8
- Spatially-varying Regularization with Conditional Transformer for Unsupervised Image Registration7
An end-to-end framework that uses neural networks to learn a spatially-varying deformation regularizer directly from data and the hyperparameter of the proposed regularizer is conditioned into the network, enabling easy tuning of the regularization strength.
- 7
- Pretraining Deformable Image Registration Networks with Random Images6
Using registration between random images as a proxy task for pretraining a foundation model for image registration improves registration accuracy, reduces the amount of domain-specific data needed to achieve competitive performance, and accelerates convergence during downstream training, thereby enhancing computational efficiency.
- A Preliminary Exploration Towards General Image Restoration6
This paper delineates the essential aspects of GIR, including problem definition and the overarching significance of generalization performance, and conducts a comprehensive evaluation of existing approaches for tackling the GIR challenge, illuminating their strengths and pragmatic challenges.
- 6
- 6
- Towards Efficient SDRTV-to-HDRTV by Learning From Image Formation5
This paper delineates and analyzes the SDRTV-to-HDRTV conversion by modeling the formation of SDRTV/HDRTV content, and proposes a new three-step solution called HDRTVNet++, which includes adaptive global color mapping, local enhancement, and highlight refinement.
- An Integrated Segmentation Framework Utilizing Mamba Fusion for Optical and SAR Images5
A segmentation framework based on Mamba fusion of optical and SAR images is proposed, which outperforms other state‐of‐the‐art deep learning approaches, achieving an overall accuracy (OA) of 84.13%, compared to 76.29% for the Kappa statistic.
- dARt Vinci: Egocentric Data Collection for Surgical Robot Learning at Scale5
dARt Vinci is introduced, a scalable data collection platform for robot learning in surgical settings that uses Augmented Reality (AR) hand tracking and a high-fidelity physics engine to capture subtle maneuvers in primitive surgical tasks.
- Realtime Robust Shape Estimation of Deformable Linear Object5
The real-world experiments of tracking and estimating a heavy-load cable prove that the proposed approach to estimate the shape of linear deformable objects in realtime is robust under occlusion and complex entanglement scenarios.
- 5
- 5
- LEADER-FOLLOWER COOPERATIVE LOCALIZATION BASED ON VIO / UWB LOOSE COUPLING FOR AGV GROUP4
This paper introduces the plane constraint with SE(2) into VIO to suppress drift in 2D motion and proposes a Leader-Follower cooperative localization system for AGV group, which equipped with camera/IMU/ UWB anchors as the Leader and IMU/UWB tags as the Follower.
- MSRepaint: Multiple Sclerosis Repaint with conditional denoising diffusion implicit model for bidirectional lesion filling and synthesis3
MSRepaint's unified bidirectional filling and synthesis capability, with full spatial control over lesion appearance, enables high-fidelity mask-conditioned voxel-wise control of lesion appearance within a unified framework.
- 3
- A Roadmap Towards Automated and Regulated Robotic Systems3
It is argued that the unregulated generative processes from AI is fitted for low level end tasks, but intervention in the form of manual or automated regulation should happen post-workflow-generation and pre-robotic-execution.
- 3
- 3
- Phenotype discovery of traumatic brain injury segmentations from heterogeneous multi-site data2
Differences originated in 1) the brainstem, occipital pole and structures posterior to the orbit, 2) subcortical gray matter and insular cortex, and 3) cerebral and cerebellar white matter using independent component analysis and clustering the component loadings of those with TBI.
- Correlation ratio for unsupervised learning of multi-modal deformable registration2
This work proposes a differentiable correlation ratio to use as a loss function for learning-based multi-modal deformable image registration, and extends the traditionally non-differentiable implementation of the correlation ratio by using the Parzen windowing approximation, enabling backpropagation with deep neural networks.
- 2
- On the Fly Robotic-Assisted Medical Instrument Planning and Execution Using Mixed Reality2
A novel framework using mixed reality technologies to ease the use of RAMS achieves real-time planning and execution of medical instruments by providing 3D anatomical image overlay, human-robot collision detection, and robot programming interface.
- DRIMET: Deep Registration for 3D Incompressible Motion Estimation in Tagged-MRI with Application to the Tongue2
This paper presents a novel unsupervised phase-based 3D motion estimation technique for tagged MRI that outperforms existing approaches, and also exhibits improvements in speed, robustness to tag fading, and large tongue motion.
- 2
- 2
- 2
- 2
- 2
- SACT: A New Model of Covert Communication Based on SDN2
A new anonymous communication tracking model SDN-based Anonymous Communication Tracking (SACT), which introduces network watermarking into SDN and combines IP time hidden channel and symbol expansion technology and introduces a hopping protection mechanism to improve the anti detection ability of the watermark.
- LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution1
This work provides the first robust methodology for applying Linear Attention in the photorealistic SR domain, establishing a foundational paradigm for future research in efficient generative super-resolution.
- 1
- Investigating the impact of kernel harmonization and deformable registration on inspiratory and expiratory chest CT images for people with COPD1
A two-stage pipeline to harmonize reconstruction kernels between paired inspiratory-expiratory scans and perform deformable image registration for data acquired from the COPD Gene study is proposed and harmonization significantly reduces inconsistencies in emphysema measurement.
- 1
- Robust body composition analysis by generating 3D CT volumes from limited 2D slices1
A novel method to generate 3D CT volumes from limited number of 2D slices using a latent diffusion model (LDM) is presented, demonstrating that the proposed method significantly enhances body composition analysis compared to traditional 2D-based analysis.
- 1
- MetaVoxel: Joint Diffusion Modeling of Imaging and Clinical Metadata1
MetaVoxel is introduced, a generative joint diffusion modeling framework that models the joint distribution over imaging data and clinical metadata by learning a single diffusion process spanning all variables, and demonstrates that joint multimodal diffusion offers a promising direction for unifying medical AI models and enabling broader clinical applicability.
- Hierarchical attention transformer provides assistant suggestions for orbital rejuvenation surgery1
The HATrans model represents a significant advancement in multi-label classification for facial aesthetics, offering a practical solution for early periocular aging detection at home and its robust performance supports its potential for assisting clinical decision-making in cosmetic surgery.
- Beyond the lungs: extending the field-of-view in chest CT with latent diffusion models1
The approach first trains a variational autoencoder to encode 2D axial CT slices individually, then stacks the latent representations of the VAE to form a 3D context for training a latent diffusion model, and extends the FOV of CT images in the z-direction by generating new axial slices in a zero-shot manner.
- Investigating effects of air quality and weather on human brain volumes1
The findings underscore the importance of considering a broad range of environmental factors in neuroimaging studies and suggest that air quality and seasonal influences can be confounds in studies investigating variations in structural brain volumes.
- Unsupervised Learning of Multi-modal Affine Registration for PET/CT1
This study introduces a novel method using Parzen windowing to approximate the correlation ratio, which acts as the image similarity measure for training DNNs in multi-modal registration and proposes a multi-scale, instance-specific optimization scheme that iteratively refines the DNN-generated affine parameters across multiple image resolutions.
- 1
- 1
- 1
- –
- Mpox lesion counting with semantic and instance segmentation methods–
Instance segmentation methods and UNet-based semantic segmentation methods performed equally well in lesion counting, but the ensemble of the trained models showed no performance increase over the best-performing model UNet, likely because errors are frequently shared across models.
- Longitudinal Masked Representation Learning for Pulmonary Nodule Diagnosis from Language Embedded EHRs–
It is suggested that language-embedded MRL can facilitate downstream clinical classification, offering potential advancements in the comprehensive analysis of longitudinal EHR modalities.
- –
- Deep Automatic Alignment of Mpox Dermatological Hand Photography–
This work introduces a novel application of deep learning for lesion monitoring through alignment of dermatological hand photographs by adapting the VoxelMorph framework for 2D photographic data, and explores key point alignment across serial images.
- –
- –
- –
- SM4Depth: Seamless Monocular Metric Depth Estimation across Multiple Cameras and Scenes by One Model–
- –
- –
- –
- –
- –
- Investigation and Application of Digital Image Correlation Technology in Vibration Measurement Based on Two Cameras–
This paper uses BUMBLEBEE binocular stereo cameras to shoot the images of test object, and a MATLAB program is developed to revert the coordinates of every pixel, reduce noise, and generate stereo images.
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 2026-10-14. 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.