Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks130 from public data
- MAT: Mask-Aware Transformer for Large Hole Image Inpainting539
A novel transformer-based model for large hole inpainting is presented, which unifies the merits of transformers and convolutions to efficiently process high-resolution images.
- Video-P2P: Video Editing with Cross-Attention Control391
This work proposes to first tune a Text-to-Set (T2S) model to complete an approximate inversion and then optimize a shared unconditional embedding to achieve accurate video inversion with a small memory cost, and proves that it is crucial for consistent video editing.
- ControlNeXt: Powerful and Efficient Control for Image and Video Generation200
This paper designs a more straightforward and efficient architecture, replacing heavy additional branches with minimal additional cost compared to the base model, and proposes another method called Cross Normalization (CN) as a replacement for Zero-Convolution' to achieve fast and stable training convergence.
- MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution199
The MASA network for RefSR is proposed, where two novel modules are designed to address the problems of high-quality correspondence matching and the computational cost by a coarse-to-fine correspondence matching scheme.
- MuCAN: Multi-correspondence Aggregation Network for Video Super-Resolution185
This work proposes a temporal multi-correspondence aggregation strategy to leverage similar patches across frames, and a cross-scale nonlocal-cor correspondence aggregation scheme to explore self-similarity of images across scales.
- On Efficient Transformer-Based Image Pre-training for Low-Level Vision146
To comprehensively diagnose the influence of pre-training, a whole set of principled evaluation tools are designed that uncover its effects on internal representations, revealing that multi-related-task pre- training is more effective and data-efficient than other alternatives.
- 108
- Best-Buddy GANs for Highly Detailed Image Super-resolution95
This work considers the single image super-resolution (SISR) problem, and proposes best-buddy GANs (Beby-GAN) for rich-detail SISR, a region-aware adversarial learning strategy that directs the model to focus on generating details for textured areas adaptively.
- CoSeR: Bridging Image and Language for Cognitive Super-Resolution93
The Cognitive Super-Resolution (CoSeR) framework is introduced, empowering SR models with the capacity to comprehend low-resolution images and a novel condition injection scheme called “Ali-in-Attention ”, consolidating all conditional information into a single module.
- 90
- Texture Generation on 3D Meshes with Point-UV Diffusion89
Point-UV diffusion, a coarse-to-fine pipeline that marries the denoising diffusion model with UV mapping to generate 3D consistent and high-quality texture images in UV space, is presented.
- 83
- JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration55
JarvisIR, a VLM-powered agent that leverages the VLM as a controller to manage multiple expert restoration models to enhance system robustness, reduce hallucinations, and improve generalizability in real-world adverse weather, is proposed.
- 53
- 52
- 52
- NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer44
This work proposes NeRFLiX, a general NeRF-agnostic restorer paradigm by learning a degradation-driven inter-viewpoint mixer that is able to fuse highly related high-quality training images, pushing the performance of cutting-edge NeRF models to entirely new levels and producing highly photo-realistic synthetic views.
- Video Demoiréing with Relation-Based Temporal Consistency43
A relation-based temporal consistency loss is proposed to encourage the model to learn temporal consistency priors directly from ground-truth reference videos, which facilitates producing temporally consistent predictions and effectively maintains frame-level qualities.
- POSTA: A Go-to Framework for Customized Artistic Poster Generation42
This work presents POSTA: a modular framework powered by diffusion models and multimodal large language models for customized artistic poster generation, which demonstrates POSTA’s exceptional controllability and design diversity, outperforming existing models in both text accuracy and aesthetic quality.
- One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation42
This work proposes FluxSR, a novel one-step diffusion Real-ISR technique based on flow matching models that outperforms existing one-step diffusion-based Real-ISR methods and proposes TV-LPIPS as a perceptual loss and Attention Diversification Loss as a regularization term to reduce token similarity in transformer, thereby eliminating high-frequency artifacts.
- Revisiting Temporal Alignment for Video Restoration40
This work presents a novel, generic iterative alignment module which employs a gradual refinement scheme for sub-alignments, yielding more accurate motion compensation and a non-parametric re-weighting method, where the importance of each neighboring frame is adaptively evaluated in a spatial-wise way for aggregation.
- Efficient Real-World Image Super-Resolution Via Adaptive Directional Gradient Convolution38
A novel equivalent parameter fusion method for DGConv is devised that maintains its rich representational capabilities while keeping computational costs consistent with a single Vanilla Convolution (VConv), enabling DGConv to improve the performance of existing super-resolution networks without incurring additional computational expenses.
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning37
This work introduces a novel “Low-Res Leads the Way” (LWay) training framework, merging Supervised Pre-training with Self-supervised Learning to enhance the adaptability of SR models to real-world images.
- MC 2 : Multi-concept Guidance for Customized Multi-concept Generation34
MC2 is proposed, a novel approach for multi-concept customization that enhances flexibility and fidelity through inference-time optimization and can be seamlessly applied to text-to-image generation, providing robust compositional capabilities.
- 34
- Dual Prompting Image Restoration with Diffusion Transformers33
This paper introduces DPIR (Dual Prompting Image Restoration), a novel image restoration method that effectivly extracts conditional information of low-quality images from multiple perspectives and delivers superior image restoration performance.
- QMambaBSR: Burst Image Super-Resolution with Query State Space Model32
A novel Query Mamba Burst Super-Resolution (QMambaBSR) network is introduced and an Adaptive Upsampling (AdaUp) module is proposed that dynamically adjusts the upsampling kernel to suit the characteristics of different burst scenes, achieving superior detail reconstruction.
- 2D MoTe 2 /MoS 2−x O x Van der Waals Heterostructure for Bimodal Neuromorphic Optoelectronic Computing32
A memristor synaptic device is reported that utilizes the ion migration properties of MoTe2/MoS2−xOx heterojunction interface and demonstrates remarkable exceptional linearity, extensive dynamic regulation, and bidirectional independently controllable synaptic plasticity when subjected to bimodal regulation using electrical and optical signals.
- 32
- 30
- 29
- High speed all-optical encryption and decryption using quantum dot semiconductor optical amplifiers29
Results show that this scheme can realize all-optical encryption and decryption by using key-stream generators at high speed (~250 Gb/s).
- Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolution27
This paper argues that key image processing steps in Image Signal Processing, such as denoising and demosaicing, inherently result in the loss of fine details in LR images, making LR RAW a valuable information source, and pioneers the use of details hidden in RAW data to complement existing RGB-only methods, yielding superior outputs.
- Parameter-Adaptive VMD Method Based on BAS Optimization Algorithm for Incipient Bearing Fault Diagnosis27
The experimental results demonstrate that the proposed method is more effective in extracting the incipient bearing fault characteristics than the existing VMD method.
- Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation26
A simple, efficient O (N) yet powerful guided cross-scale pyramid alignment (GCSPA) module, where multi-scale information is highly exploited, and the efficiency and effectiveness of the proposed strategy are justified.
- 25
- 22
- 22
- Metric entropy of high dimensional distributions22
The metric entropy of F d under the L 2 ([0,1] d ) norm is studied and connections with small deviation probability for Brownian sheets under the sup-norm are established.
- Fast Image Super-Resolution via Consistency Rectified Flow21
This work proposes FlowSR, a novel approach that reformulates the SR problem as a rectified flow from low-resolution (LR) to high-resolution (HR) images, and refine the original consistency distillation process by incorporating HR regularization, ensuring that the learned SR flow not only enforces self-consistency but also converges precisely to the ground-truth HR target.
- What Makes for Good Tokenizers in Vision Transformer?21
This work investigates what makes for a good tokenizer in computer vision from an information trade-off perspective, and proposes the proposed Modulation across Tokens (MoTo), which incorporates inter-token modeling capability through normalization.
- Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis18
This work proposes Turbo2K, an efficient and practical framework for generating detail-rich 2K videos while significantly improving training and inference efficiency, and designs a hierarchical two-stage synthesis framework that first generates multi-level feature at lower resolutions before guiding high-resolution video generation.
- Image Inpainting via Iteratively Decoupled Probabilistic Modeling18
A novel spatial diffusion model (SDM) that uses a few iterations to gradually deliver informative pixels to the entire image, largely enhancing the inference efficiency and achieves high-quality large-hole completion.
- Formation Control of a Multi-Autonomous Underwater Vehicle Event-Triggered Mechanism Based on the Hungarian Algorithm18
The Hungarian algorithm proposed in this paper can deal with the leader failure in the multi-AUV leader–follower formation, and the ETM designed in this document can reduce about 90% of the communication traffic of the formation, which also proves the highly efficient performance of the improved ETM in the paper.
- 17
- Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal17
Experimental results demonstrate that CODiff surpasses recent leading methods in both quantitative and visual quality metrics, and a dual learning strategy for CaVE, which combines explicit and implicit learning allows for a deeper understanding of JPEG compression.
- 17
- 17
- 16
- Exploiting Multiple Correlations Among Urban Regions for Crowd Flow Prediction15
This work leverage multiple spatial correlations and the temporal dependency to build an urban flow prediction framework that uses only a little recent data as the input but can mine rich internal modes and can mitigate the influence of the instability of data distributions in highly dynamic environments for prediction.
- 15
- 15
- A High-Performance Accelerator for Super-Resolution Processing on Embedded GPU14
A full-stack SR acceleration framework on embedded GPU devices is implemented that outperforms the state-of-the-art NVIDIA TensorRT significantly and can achieve real-time performance.
- Finite element discretizations of nonlocal minimal graphs: Convergence14
A finite element discretization for the computation of fractional minimal graphs of order s in (0,1/2) on a bounded domain $\Omega$ is proposed and a geometric notion of error is introduced that, for any pair of $H^1$ functions, in the limit $s \to 1/2$ recovers a weighted $L^2$-discrepancy between the normal vectors to their graphs.
- Post-processing of interpolation-based super-resolution mapping with morphological filtering and fraction refilling13
The results show that the proposed post-processing algorithm increases the accuracy of the super-resolution land-cover map and is suitable for different interpolation-based SRM models.
- 12
- From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm11
This work proposes NeRFLiX, a general NeRF-agnostic restorer paradigm that learns a degradation-driven inter-viewpoint mixer and presents NeRFLiX++, a stronger two-stage NeRF degradation simulator and a faster inter-viewpoint mixer, achieving superior performance with significantly improved computational efficiency.
- 11
- AVG-LLaVA: An Efficient Large Multimodal Model with Adaptive Visual Granularity10
This work introduces AVG-LLaVA, an LMM that can adaptively select the appropriate visual granularity based on the input image and instruction, and proposes RGLF, a novel training paradigm that aims at aligning the granularity predicted by the router with the preferences of the LMM, without the need for additional manually annotated data.
- Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment9
Dog-IQA, a standard-guided zero-shot mix-grained IQA method, which is training-free and utilizes the exceptional prior knowledge of multimodal large language models (MLLMs) to obtain accurate IQA scores, is proposed.
- HRPGAN: A GAN-based Model to Generate High-resolution Remote Sensing Images9
Experimental results show that the proposed HRPGAN model generates the more diverse and lifelike images in HR remote sensing generation than Bicubic method and TGAN model.
- Multi-microgrids system reliability assessment algorithm considering energy dispatch strategy among microgrids9
A reliability assessment algorithm is proposed which considers energy exchanges and dispatching strategy among microgrids in a multi-microgrids system and is applied to a reliability evaluation study, which shows that the proposed model and assessment algorithm can be effectively utilized by planners to conduct reliability evaluation of a multiple microgrid system.
- A big data approach to artificial intelligence driven predictive modelling for optimizing material properties in additive manufacturing7
A novel Multistage Transfer Learning Model (MTLM) for predicting MP in powder bed fusion-based AM is presented, demonstrating strong generalization and achieving MP prediction accuracies of over 93%.
- Segment Any-Quality Images with Generative Latent Space Enhancement7
Gle-SAM utilizes Generative Latent space Enhancement to boost robustness on low-quality images, thus enabling generalization across various image qualities and significantly improves segmentation robustness on complex degradations while maintaining generalization to clear images.
- 6
- 6
- 6
- BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution5
BiMaCoSR is proposed, which combines binarization and one-step distillation to obtain extreme compression and acceleration and outperforms current state-of-the-art binarization methods and gains competitive performance compared with FP one-step model.
- 5
- 5
- 5
- Recent Progress in Some Active Topics on Complex Networks5
By combining the results of different research orientations, a review of the recent advances in regards to spectral graph theory, opinion dynamics, interdependent networks, graph energy theory and temporal networks is provided.
- 5
- 4
- 4
- 4
- 4
- Measuring fractal dimension of metro systems4
Measurements show that for small network systems, box-covering method gives a better scaling relation and both unweighted and weighted metro networks with optimal box-Covering method are measured.
- SODiff: Semantic-Oriented Diffusion Model for JPEG Compression Artifacts Removal3
This work proposes SODiff, a novel and efficient semantic-oriented one-step diffusion model for JPEG artifacts removal that incorporates a semantic-aligned image prompt extractor (SAIPE) and proposes a quality factor-aware time predictor that implicitly learns the compression quality factor of the LQ image and adaptively selects the optimal denoising start timestep for the diffusion process.
- 3
- A Gradient-Based Algorithm with Nonmonotone Line Search for Nonnegative Matrix Factorization3
A modified nonmonotone line search rule is suggested, in which a new parameter formula is introduced to control the degree of the nonmonotonicity of line search, and a global convergent method to solve the NMF based on the alternating nonnegative least squares framework is proposed.
- 3
- 3
- 3
- 3
- 3
- Detection for steganography based on Hilbert Huang Transform3
The Hilbert-Huang Transform for Analysis of Universal blind steganalysis detection task uses its efficient unsteady-state modeling ability to constucte features of steganography object and adopt independent variable analysis method to extract and refine feature.
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- MHGCL: Combining Motif and Homogeneity in graph contrastive learning1
This paper introduces the Motif and Homogeneity based Graph Contrastive Learning (MHGCL) approach, integrating higher-order graph characteristics and graph homophily within a single framework, and achieves significant performance improvements across different Graph Contrastive Learning (GCL) tasks.
- 1
- BiDense: Binarization for Dense Prediction1
BiDense, a generalized binary neural network designed for efficient and accurate dense prediction tasks, incorporates two key techniques: the Distribution-adaptive Binarizer (DAB) and the Channel-adaptive Full-precision Bypass (CFB).
- Efficient Nonnegative Matrix Factorization via Modified Monotone Barzilai-Borwein Method with Adaptive Step Sizes Strategy1
An active set adaptive monotone projected Barzilai-Borwein method for solving nonnegative matrix factorization (NMF) based on the alternating nonnegative least squares framework, in which the Barzilai-Borwein (BB) step sizes can be adaptively picked to get meaningful convergence rate improvements.
- 1
- 1
- 1
- A Detection Method of Dense Harmonics/Inter-harmonics Based on Improved All-phase Time-shifting Method and ZoomFFT1
Simulation results show that the proposed algorithm can effectively and accurately extract the frequency, amplitude and phase parameters of dense harmonics/inter-harmonics under the conditions of multiple dense spectrum, fluctuation of fundamental frequency and noise interference.
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- [Evaluation of the function and activity of masticatory muscles using a self-developed wireless surface electromyography system].–
Oralmetry and the two commercial sEMG devices demonstrated good repeatability in capturing sEMG indicators for evaluating masticatory muscle function, and all three devices exhibited good consistency in measuring sEMG indicators.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.