{"total":160,"rows":[{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245,"area":null},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505,"area":null},{"id":"2302.13848","title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation","created":"2023-02-27","cited_by_count":416,"area":null},{"id":"2401.13627","title":"Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild","created":"2024-01-24","cited_by_count":286,"area":null},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238,"area":null},{"id":"2203.13777","title":"Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion","created":"2022-03-25","cited_by_count":185,"area":null},{"id":"2406.02918","title":"U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation","created":"2024-06-05","cited_by_count":179,"area":null},{"id":"2311.03335","title":"Cross-Image Attention for Zero-Shot Appearance Transfer","created":"2023-11-06","cited_by_count":136,"area":null},{"id":"2403.11641","title":"Arc2Face: A Foundation Model for ID-Consistent Human Faces","created":"2024-03-18","cited_by_count":101,"area":null},{"id":"2210.11841","title":"Diffusion Visual Counterfactual Explanations","created":"2022-10-21","cited_by_count":96,"area":null},{"id":"2206.07632","title":"Exploring Chemical Space with Score-based Out-of-distribution Generation","created":"2022-06-06","cited_by_count":95,"area":null},{"id":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89,"area":null},{"id":"2311.16845","title":"Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration","created":"2023-11-28","cited_by_count":88,"area":null},{"id":"2303.06885","title":"DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration","created":"2023-03-13","cited_by_count":79,"area":null},{"id":"2207.03442","title":"Back to the Source: Diffusion-Driven Test-Time Adaptation","created":"2022-07-07","cited_by_count":71,"area":null},{"id":"2203.12621","title":"MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion","created":"2022-03-23","cited_by_count":67,"area":null},{"id":"2206.13295","title":"Diffusion Deformable Model for 4D Temporal Medical Image Generation","created":"2022-06-27","cited_by_count":65,"area":null},{"id":"2303.01818","title":"Word-As-Image for Semantic Typography","created":"2023-03-03","cited_by_count":63,"area":null},{"id":"2404.01050","title":"Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation","created":"2024-04-01","cited_by_count":51,"area":null},{"id":"2304.11134","title":"Plug-and-Play split Gibbs sampler: embedding deep generative priors in Bayesian inference","created":"2023-04-21","cited_by_count":42,"area":null},{"id":"2311.15100","title":"Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation","created":"2023-11-25","cited_by_count":33,"area":null},{"id":"2304.05818","title":"Gradient-Free Textual Inversion","created":"2023-04-12","cited_by_count":29,"area":null},{"id":"2303.16976","title":"MaLP: Manipulation Localization Using a Proactive Scheme","created":"2023-03-29","cited_by_count":26,"area":null},{"id":"2304.06094","title":"Energy-guided Entropic Neural Optimal Transport","created":"2023-04-12","cited_by_count":26,"area":null},{"id":"2303.10406","title":"3DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process","created":"2023-03-18","cited_by_count":25,"area":null},{"id":"2306.08328","title":"Distribution Shift Inversion for Out-of-Distribution Prediction","created":"2023-06-14","cited_by_count":23,"area":null},{"id":"2306.01433","title":"Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach","created":"2023-06-02","cited_by_count":21,"area":null},{"id":"2403.14611","title":"Explorative Inbetweening of Time and Space","created":"2024-03-21","cited_by_count":21,"area":null},{"id":"2207.09542","title":"Controllable Data Generation by Deep Learning: A Review","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2409.03944","title":"HUMOS: Human Motion Model Conditioned on Body Shape","created":"2024-09-05","cited_by_count":20,"area":null},{"id":"2403.09093","title":"Desigen: A Pipeline for Controllable Design Template Generation","created":"2024-03-14","cited_by_count":19,"area":null},{"id":"2405.05953","title":"Frame Interpolation with Consecutive Brownian Bridge Diffusion","created":"2024-05-09","cited_by_count":19,"area":null},{"id":"2303.16765","title":"MDP: A Generalized Framework for Text-Guided Image Editing by Manipulating the Diffusion Path","created":"2023-03-29","cited_by_count":18,"area":null},{"id":"2404.01692","title":"Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss","created":"2024-04-02","cited_by_count":18,"area":null},{"id":"2310.11838","title":"Equivariant Bootstrapping for Uncertainty Quantification in Imaging Inverse Problems","created":"2023-10-18","cited_by_count":17,"area":null},{"id":"2408.12128","title":"Diffusion-Based Visual Art Creation: A Survey and New Perspectives","created":"2024-08-22","cited_by_count":17,"area":null},{"id":"2401.12467","title":"An open dataset for the evolution of oracle bone characters: EVOBC","created":"2024-01-23","cited_by_count":16,"area":null},{"id":"2503.20349","title":"Consistency Trajectory Matching for One-Step Generative Super-Resolution","created":"2025-03-26","cited_by_count":16,"area":null},{"id":"2409.02979","title":"Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors","created":"2024-09-04","cited_by_count":15,"area":null},{"id":"2412.20104","title":"SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis","created":"2024-12-28","cited_by_count":14,"area":null},{"id":"2503.20782","title":"Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising","created":"2025-03-26","cited_by_count":14,"area":null},{"id":"2406.04239","title":"Solving Inverse Problems in Protein Space Using Diffusion-Based Priors","created":"2024-06-06","cited_by_count":13,"area":null},{"id":"2407.08256","title":"Adaptive Compressed Sensing with Diffusion-Based Posterior Sampling","created":"2024-07-11","cited_by_count":13,"area":null},{"id":"2409.10966","title":"CUNSB-RFIE: Context-aware Unpaired Neural Schr\\\"odinger Bridge in Retinal Fundus Image Enhancement","created":"2024-09-17","cited_by_count":13,"area":null},{"id":"2310.16047","title":"From Posterior Sampling to Meaningful Diversity in Image Restoration","created":"2023-10-24","cited_by_count":12,"area":null},{"id":"2411.05330","title":"Inversion-based Latent Bayesian Optimization","created":"2024-11-08","cited_by_count":11,"area":null},{"id":"2303.09760","title":"Diffusing the Optimal Topology: A Generative Optimization Approach","created":"2023-03-17","cited_by_count":10,"area":null},{"id":"2409.14587","title":"Deep Learning Techniques for Atmospheric Turbulence Removal: A Review","created":"2024-09-03","cited_by_count":10,"area":null},{"id":"2503.12472","title":"Diffusion-based Synthetic Data Generation for Visible-Infrared Person Re-Identification","created":"2025-03-16","cited_by_count":10,"area":null},{"id":"2311.14294","title":"Decouple Content and Motion for Conditional Image-to-Video Generation","created":"2023-11-24","cited_by_count":9,"area":null},{"id":"2403.01124","title":"Text-guided Explorable Image Super-resolution","created":"2024-03-02","cited_by_count":9,"area":null},{"id":"2510.15868","title":"LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal","created":"2025-10-17","cited_by_count":9,"area":null},{"id":"2510.19618","title":"Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism","created":"2025-10-22","cited_by_count":9,"area":null},{"id":"2303.16280","title":"UVCGAN v2: An Improved Cycle-Consistent GAN for Unpaired Image-to-Image Translation","created":"2023-03-28","cited_by_count":8,"area":null},{"id":"2305.03051","title":"Controllable Visual-Tactile Synthesis","created":"2023-05-04","cited_by_count":8,"area":null},{"id":"2412.16748","title":"Solving Inverse Problems via Diffusion Optimal Control","created":"2024-12-21","cited_by_count":8,"area":null},{"id":"2502.09655","title":"Bidirectional Diffusion Bridge Models","created":"2025-02-12","cited_by_count":8,"area":null},{"id":"2506.04490","title":"Multiscale guidance of protein structure prediction with heterogeneous cryo-EM data","created":"2025-06-04","cited_by_count":8,"area":null},{"id":"2403.18461","title":"An Efficient and Harmonized Framework for Balanced Cross-Domain Feature Integration","created":"2024-03-27","cited_by_count":7,"area":null},{"id":"2409.10202","title":"SteeredMarigold: Steering Diffusion Towards Depth Completion of Largely Incomplete Depth Maps","created":"2024-09-16","cited_by_count":7,"area":null},{"id":"2511.16854","title":"MRI Super-Resolution with Deep Learning: A Comprehensive Survey","created":"2025-11-20","cited_by_count":7,"area":null},{"id":"2301.13743","title":"Zero-shot-Learning Cross-Modality Data Translation Through Mutual Information Guided Stochastic Diffusion","created":"2023-01-31","cited_by_count":6,"area":null},{"id":"2305.05014","title":"Solving Linear Inverse Problems using Higher-Order Annealed Langevin Diffusion","created":"2023-05-08","cited_by_count":6,"area":null},{"id":"2310.00362","title":"Diffusion Posterior Illumination for Ambiguity-aware Inverse Rendering","created":"2023-09-30","cited_by_count":6,"area":null},{"id":"2402.06446","title":"ControlUDA: Controllable Diffusion-assisted Unsupervised Domain Adaptation for Cross-Weather Semantic Segmentation","created":"2024-02-09","cited_by_count":6,"area":null},{"id":"2408.13922","title":"COMPOSE: Comprehensive Portrait Shadow Editing","created":"2024-08-25","cited_by_count":6,"area":null},{"id":"2412.19009","title":"FACEMUG: A Multimodal Generative and Fusion Framework for Local Facial Editing","created":"2024-12-26","cited_by_count":6,"area":null},{"id":"2504.03006","title":"DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recovery","created":"2025-04-03","cited_by_count":6,"area":null},{"id":"2311.15445","title":"FLAIR: A Conditional Diffusion Framework with Applications to Face Video Restoration","created":"2023-11-26","cited_by_count":5,"area":null},{"id":"2401.09742","title":"Image Translation as Diffusion Visual Programmers","created":"2024-01-18","cited_by_count":5,"area":null},{"id":"2403.13680","title":"Step-Calibrated Diffusion for Biomedical Optical Image Restoration","created":"2024-03-20","cited_by_count":5,"area":null},{"id":"2410.02078","title":"Posterior sampling via Langevin dynamics based on generative priors","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2504.07696","title":"Conformalized Generative Bayesian Imaging: An Uncertainty Quantification Framework for Computational Imaging","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2509.25186","title":"Guided Diffusion for the Discovery of New Superconductors","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2310.00277","title":"A Unified Framework for Generative Data Augmentation: A Comprehensive Survey","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2311.07414","title":"FIRST: A Million-Entry Dataset for Text-Driven Fashion Synthesis and Design","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2311.17744","title":"Variational Bayes image restoration with compressive autoencoders","created":"2023-11-29","cited_by_count":4,"area":null},{"id":"2312.02235","title":"CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy","created":"2023-12-04","cited_by_count":4,"area":null},{"id":"2312.14579","title":"Synthesizing Environment-Specific People in Photographs","created":"2023-12-22","cited_by_count":4,"area":null},{"id":"2404.09051","title":"Rethinking Iterative Stereo Matching from Diffusion Bridge Model Perspective","created":"2024-04-13","cited_by_count":4,"area":null},{"id":"2405.18075","title":"Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient","created":"2024-05-28","cited_by_count":4,"area":null},{"id":"2407.12842","title":"MS2SL: Multimodal Spoken Data-Driven Continuous Sign Language Production","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2409.13930","title":"RN-SDEs: Limited-Angle CT Reconstruction with Residual Null-Space Diffusion Stochastic Differential Equations","created":"2024-09-20","cited_by_count":4,"area":null},{"id":"2503.15056","title":"Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation","created":"2025-03-19","cited_by_count":4,"area":null},{"id":"2312.16197","title":"INFAMOUS-NeRF: ImproviNg FAce MOdeling Using Semantically-Aligned Hypernetworks with Neural Radiance Fields","created":"2023-12-23","cited_by_count":3,"area":null},{"id":"2402.03981","title":"Controllable Diverse Sampling for Diffusion Based Motion Behavior Forecasting","created":"2024-02-06","cited_by_count":3,"area":null},{"id":"2407.12401","title":"Geometric Remove-and-Retrain (GOAR): Coordinate-Invariant eXplainable AI Assessment","created":"2024-07-17","cited_by_count":3,"area":null},{"id":"2410.03787","title":"CalliffusionV2: Personalized Natural Calligraphy Generation with Flexible Multi-modal Control","created":"2024-10-03","cited_by_count":3,"area":null},{"id":"2503.12124","title":"Z-Magic: Zero-shot Multiple Attributes Guided Image Creator","created":"2025-03-15","cited_by_count":3,"area":null},{"id":"2509.09427","title":"FS-Diff: Semantic guidance and clarity-aware simultaneous multimodal image fusion and super-resolution","created":"2025-09-11","cited_by_count":3,"area":null},{"id":"2511.17038","title":"DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing","created":"2025-11-21","cited_by_count":3,"area":null},{"id":"2603.12057","title":"Adaptive Weighted h-Transform Sampling for Coarse-Guided Visual Generation","created":"2026-03-12","cited_by_count":3,"area":null},{"id":"2308.07665","title":"Inversion-by-Inversion: Exemplar-based Sketch-to-Photo Synthesis via Stochastic Differential Equations without Training","created":"2023-08-15","cited_by_count":2,"area":null},{"id":"2311.06297","title":"STRIDE: Structure-guided Generation for Inverse Design of Molecules","created":"2023-11-06","cited_by_count":2,"area":null},{"id":"2312.10899","title":"MagicScroll: Nontypical Aspect-Ratio Image Generation for Visual Storytelling via Multi-Layered Semantic-Aware Denoising","created":"2023-12-18","cited_by_count":2,"area":null},{"id":"2404.01102","title":"Diffusion based Zero-shot Medical Image-to-Image Translation for Cross Modality Segmentation","created":"2024-04-01","cited_by_count":2,"area":null},{"id":"2407.01905","title":"Enhancing Multi-Class Anomaly Detection via Diffusion Refinement with Dual Conditioning","created":"2024-07-02","cited_by_count":2,"area":null},{"id":"2411.19182","title":"SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2412.20924","title":"HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularization","created":"2024-12-30","cited_by_count":2,"area":null},{"id":"2503.08501","title":"Learning to Match Unpaired Data with Minimum Entropy Coupling","created":"2025-03-11","cited_by_count":2,"area":null}],"next_cursor":"100"}