{"total":57,"rows":[{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906,"area":null},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505,"area":null},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464,"area":null},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304,"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":"2308.07926","title":"CoDeF: Content Deformation Fields for Temporally Consistent Video Processing","created":"2023-08-15","cited_by_count":108,"area":null},{"id":"2401.10208","title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer","created":"2024-01-18","cited_by_count":80,"area":null},{"id":"2211.11138","title":"Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training","created":"2022-11-21","cited_by_count":56,"area":null},{"id":"2402.13251","title":"FlashTex: Fast Relightable Mesh Texturing with LightControlNet","created":"2024-02-20","cited_by_count":56,"area":null},{"id":"2310.05590","title":"Perceptual Artifacts Localization for Image Synthesis Tasks","created":"2023-10-09","cited_by_count":43,"area":null},{"id":"2312.07322","title":"GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2303.17870","title":"GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation","created":"2023-03-31","cited_by_count":34,"area":null},{"id":"2307.14352","title":"General Image-to-Image Translation with One-Shot Image Guidance","created":"2023-07-20","cited_by_count":31,"area":null},{"id":"2403.18551","title":"Attention Calibration for Disentangled Text-to-Image Personalization","created":"2024-03-27","cited_by_count":31,"area":null},{"id":"2409.15278","title":"PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions","created":"2024-09-23","cited_by_count":31,"area":null},{"id":"2302.05496","title":"MaskSketch: Unpaired Structure-guided Masked Image Generation","created":"2023-02-10","cited_by_count":27,"area":null},{"id":"2506.16960","title":"Visual-Instructed Degradation Diffusion for All-in-One Image Restoration","created":"2025-06-20","cited_by_count":26,"area":null},{"id":"2406.05871","title":"OmniControlNet: Dual-stage Integration for Conditional Image Generation","created":"2024-06-09","cited_by_count":24,"area":null},{"id":"2307.03190","title":"Text-Guided Synthesis of Eulerian Cinemagraphs","created":"2023-07-06","cited_by_count":22,"area":null},{"id":"2403.01852","title":"PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis","created":"2024-03-04","cited_by_count":20,"area":null},{"id":"2409.04559","title":"Thinking Outside the BBox: Unconstrained Generative Object Compositing","created":"2024-09-06","cited_by_count":19,"area":null},{"id":"2409.11406","title":"Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion","created":"2024-09-17","cited_by_count":19,"area":null},{"id":"2402.15490","title":"A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends","created":"2024-02-23","cited_by_count":16,"area":null},{"id":"2301.07702","title":"Learning 3D-aware Image Synthesis with Unknown Pose Distribution","created":"2023-01-18","cited_by_count":14,"area":null},{"id":"2403.01226","title":"DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction","created":"2024-03-02","cited_by_count":13,"area":null},{"id":"2302.08641","title":"Transformer-based Generative Adversarial Networks in Computer Vision: A Comprehensive Survey","created":"2023-02-17","cited_by_count":10,"area":null},{"id":"2312.04364","title":"DemoCaricature: Democratising Caricature Generation with a Rough Sketch","created":"2023-12-07","cited_by_count":10,"area":null},{"id":"2309.03048","title":"Exploring Semantic Consistency in Unpaired Image Translation to Generate Data for Surgical Applications","created":"2023-09-06","cited_by_count":9,"area":null},{"id":"2307.12084","title":"Edge Guided GANs with Multi-Scale Contrastive Learning for Semantic Image Synthesis","created":"2023-07-22","cited_by_count":8,"area":null},{"id":"2507.00802","title":"TRACE: Temporally Reliable Anatomically-Conditioned 3D CT Generation with Enhanced Efficiency","created":"2025-07-01","cited_by_count":8,"area":null},{"id":"2307.14016","title":"RPG-Palm: Realistic Pseudo-data Generation for Palmprint Recognition","created":"2023-07-26","cited_by_count":7,"area":null},{"id":"2311.10522","title":"Enhancing Object Coherence in Layout-to-Image Synthesis","created":"2023-11-17","cited_by_count":7,"area":null},{"id":"2312.03154","title":"ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNet","created":"2023-12-05","cited_by_count":7,"area":null},{"id":"2403.09638","title":"SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis","created":"2024-03-14","cited_by_count":7,"area":null},{"id":"2507.22627","title":"LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text Pairing","created":"2025-07-30","cited_by_count":7,"area":null},{"id":"2303.03231","title":"StyO: Stylize Your Face in Only One-shot","created":"2023-03-06","cited_by_count":6,"area":null},{"id":"2412.02693","title":"Diffusion-based Visual Anagram as Multi-task Learning","created":"2024-12-03","cited_by_count":6,"area":null},{"id":"2502.06682","title":"Transfer Your Perspective: Controllable 3D Generation from Any Viewpoint in a Driving Scene","created":"2025-02-10","cited_by_count":5,"area":null},{"id":"2304.02321","title":"Few-shot Semantic Image Synthesis with Class Affinity Transfer","created":"2023-04-05","cited_by_count":4,"area":null},{"id":"2409.00522","title":"EraseDraw: Learning to Draw Step-by-Step via Erasing Objects from Images","created":"2024-08-31","cited_by_count":4,"area":null},{"id":"2409.08397","title":"360PanT: Training-Free Text-Driven 360-Degree Panorama-to-Panorama Translation","created":"2024-09-12","cited_by_count":4,"area":null},{"id":"2504.01428","title":"MuTri: Multi-view Tri-alignment for OCT to OCTA 3D Image Translation","created":"2025-04-02","cited_by_count":4,"area":null},{"id":"2305.05992","title":"MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis","created":"2023-05-10","cited_by_count":3,"area":null},{"id":"2306.02558","title":"Multi-View Representation is What You Need for Point-Cloud Pre-Training","created":"2023-06-05","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":"2305.19547","title":"Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesis","created":"2023-05-31","cited_by_count":2,"area":null},{"id":"2308.02535","title":"Learning to Generate Training Datasets for Robust Semantic Segmentation","created":"2023-08-01","cited_by_count":2,"area":null},{"id":"2510.22337","title":"GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2606.19495","title":"LooseControlVideo: Directorial Video Control using Spatial Blocking","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2308.13795","title":"VIDES: Virtual Interior Design via Natural Language and Visual Guidance","created":"2023-08-26","cited_by_count":1,"area":null},{"id":"2309.13975","title":"Diverse Semantic Image Editing with Style Codes","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2411.06583","title":"Enhancing frozen histological section images using permanent-section-guided deep learning with nuclei attention","created":"2024-11-10","cited_by_count":1,"area":null},{"id":"2505.09998","title":"From Air to Wear: Personalized 3D Digital Fashion with AR/VR Immersive 3D Sketching","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2402.08310","title":"One-to-many Reconstruction of 3D Geometry of cultural Artifacts using a synthetically trained Generative Model","created":"2024-02-13","cited_by_count":0,"area":null},{"id":"2510.12254","title":"FedMMKT:Co-Enhancing a Server Text-to-Image Model and Client Task Models in Multi-Modal Federated Learning","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2602.18309","title":"Multi-Level Conditioning by Pairing Localized Text and Sketch for Fashion Image Generation","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2603.10128","title":"HG-Lane: High-Fidelity Generation of Lane Scenes under Adverse Weather and Lighting Conditions without Re-annotation","created":"2026-03-10","cited_by_count":0,"area":null}],"next_cursor":null}