{"total":132,"rows":[{"id":"2310.02601","title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","created":"2023-10-04","cited_by_count":252,"area":"diffusion"},{"id":"2304.10530","title":"Collaborative Diffusion for Multi-Modal Face Generation and Editing","created":"2023-04-20","cited_by_count":116,"area":"diffusion"},{"id":"2503.14492","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","created":"2025-03-18","cited_by_count":106,"area":null},{"id":"2308.01661","title":"BEVControl: Accurately Controlling Street-view Elements with Multi-perspective Consistency via BEV Sketch Layout","created":"2023-08-03","cited_by_count":102,"area":null},{"id":"2401.17053","title":"BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation","created":"2024-01-30","cited_by_count":83,"area":null},{"id":"2303.14412","title":"Freestyle Layout-to-Image Synthesis","created":"2023-03-25","cited_by_count":67,"area":"diffusion"},{"id":"2306.13754","title":"Zero-shot spatial layout conditioning for text-to-image diffusion models","created":"2023-06-23","cited_by_count":64,"area":"diffusion"},{"id":"2310.15160","title":"FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models","created":"2023-10-23","cited_by_count":61,"area":null},{"id":"2212.05993","title":"RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Models","created":"2022-12-12","cited_by_count":45,"area":"diffusion"},{"id":"2211.11742","title":"SceneComposer: Any-Level Semantic Image Synthesis","created":"2022-11-21","cited_by_count":43,"area":null},{"id":"2306.04321","title":"Generative Semantic Communication: Diffusion Models Beyond Bit Recovery","created":"2023-06-07","cited_by_count":41,"area":"diffusion"},{"id":"2211.17084","title":"High-Fidelity Guided Image Synthesis with Latent Diffusion Models","created":"2022-11-30","cited_by_count":36,"area":"diffusion"},{"id":"2305.05424","title":"Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation","created":"2023-05-09","cited_by_count":34,"area":"diffusion"},{"id":"2403.13304","title":"DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception","created":"2024-03-20","cited_by_count":32,"area":null},{"id":"2309.01111","title":"ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion Models","created":"2023-09-03","cited_by_count":31,"area":"diffusion"},{"id":"2409.19365","title":"Conditional Image Synthesis with Diffusion Models: A Survey","created":"2024-09-28","cited_by_count":29,"area":"diffusion"},{"id":"2306.14132","title":"DiffMix: Diffusion Model-based Data Synthesis for Nuclei Segmentation and Classification in Imbalanced Pathology Image Datasets","created":"2023-06-25","cited_by_count":28,"area":"diffusion"},{"id":"2308.04417","title":"DiffCR: A Fast Conditional Diffusion Framework for Cloud Removal from Optical Satellite Images","created":"2023-08-08","cited_by_count":27,"area":"diffusion"},{"id":"2403.12042","title":"Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation","created":"2024-03-18","cited_by_count":27,"area":"diffusion"},{"id":"2404.15677","title":"CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models","created":"2024-04-24","cited_by_count":24,"area":"diffusion"},{"id":"2403.01852","title":"PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis","created":"2024-03-04","cited_by_count":20,"area":null},{"id":"2403.17460","title":"Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model","created":"2024-03-26","cited_by_count":20,"area":"diffusion"},{"id":"2405.20282","title":"SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow","created":"2024-05-30","cited_by_count":20,"area":"diffusion"},{"id":"2312.06712","title":"Separate-and-Enhance: Compositional Finetuning for Text2Image Diffusion Models","created":"2023-12-10","cited_by_count":19,"area":"diffusion"},{"id":"2303.07576","title":"Diffusion Models in NLP: A Survey","created":"2023-03-14","cited_by_count":16,"area":"diffusion"},{"id":"2401.16157","title":"Spatial-Aware Latent Initialization for Controllable Image Generation","created":"2024-01-29","cited_by_count":15,"area":"diffusion"},{"id":"2403.12852","title":"Generative Enhancement for 3D Medical Images","created":"2024-03-19","cited_by_count":14,"area":"diffusion"},{"id":"2404.00095","title":"GDA: Generalized Diffusion for Robust Test-time Adaptation","created":"2024-03-29","cited_by_count":14,"area":null},{"id":"2212.06458","title":"HS-Diffusion: Semantic-Mixing Diffusion for Head Swapping","created":"2022-12-13","cited_by_count":13,"area":"diffusion"},{"id":"2402.04504","title":"Text2Street: Controllable Text-to-image Generation for Street Views","created":"2024-02-07","cited_by_count":13,"area":"diffusion"},{"id":"2403.06168","title":"DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation","created":"2024-03-10","cited_by_count":13,"area":null},{"id":"2212.08861","title":"DAG: Depth-Aware Guidance with Denoising Diffusion Probabilistic Models","created":"2022-12-17","cited_by_count":12,"area":"diffusion"},{"id":"2405.04356","title":"Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation","created":"2024-05-07","cited_by_count":12,"area":null},{"id":"2211.06235","title":"HumanDiffusion: a Coarse-to-Fine Alignment Diffusion Framework for Controllable Text-Driven Person Image Generation","created":"2022-11-11","cited_by_count":11,"area":null},{"id":"2308.08157","title":"Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis","created":"2023-08-16","cited_by_count":11,"area":null},{"id":"2309.16812","title":"SatDM: Synthesizing Realistic Satellite Image with Semantic Layout Conditioning using Diffusion Models","created":"2023-09-28","cited_by_count":11,"area":"diffusion"},{"id":"2402.16506","title":"Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis","created":"2024-02-26","cited_by_count":11,"area":"diffusion"},{"id":"2312.06453","title":"Semantic Image Synthesis for Abdominal CT","created":"2023-12-11","cited_by_count":10,"area":"diffusion"},{"id":"2407.05428","title":"Diffusion as Sound Propagation: Physics-inspired Model for Ultrasound Image Generation","created":"2024-07-07","cited_by_count":10,"area":null},{"id":"2502.08960","title":"A Comprehensive Survey on Imbalanced Data Learning","created":"2025-02-13","cited_by_count":10,"area":null},{"id":"2306.00914","title":"Conditioning Diffusion Models via Attributes and Semantic Masks for Face Generation","created":"2023-06-01","cited_by_count":9,"area":"diffusion"},{"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":"2501.02526","title":"Unified Guidance for Geometry-Conditioned Molecular Generation","created":"2025-01-05","cited_by_count":9,"area":"diffusion"},{"id":"2506.23440","title":"PathDiff: Histopathology Image Synthesis with Unpaired Text and Mask Conditions","created":"2025-06-30","cited_by_count":9,"area":"diffusion"},{"id":"2302.10781","title":"Learning 3D Photography Videos via Self-supervised Diffusion on Single Images","created":"2023-02-21","cited_by_count":8,"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":"2308.01127","title":"DiffusePast: Diffusion-based Generative Replay for Class Incremental Semantic Segmentation","created":"2023-08-02","cited_by_count":8,"area":"diffusion"},{"id":"2407.14426","title":"Controllable and Efficient Multi-Class Pathology Nuclei Data Augmentation using Text-Conditioned Diffusion Models","created":"2024-07-19","cited_by_count":8,"area":"diffusion"},{"id":"2407.14434","title":"Co-synthesis of Histopathology Nuclei Image-Label Pairs using a Context-Conditioned Joint Diffusion Model","created":"2024-07-19","cited_by_count":8,"area":"diffusion"},{"id":"2409.08850","title":"DX2CT: Diffusion Model for 3D CT Reconstruction from Bi or Mono-planar 2D X-ray(s)","created":"2024-09-13","cited_by_count":8,"area":"diffusion"},{"id":"2411.13150","title":"RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation","created":"2024-11-20","cited_by_count":8,"area":"diffusion"},{"id":"2310.07131","title":"Echocardiography video synthesis from end diastolic semantic map via diffusion model","created":"2023-10-11","cited_by_count":7,"area":"diffusion"},{"id":"2311.10522","title":"Enhancing Object Coherence in Layout-to-Image Synthesis","created":"2023-11-17","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":"2404.06997","title":"Agent-driven Generative Semantic Communication with Cross-Modality and Prediction","created":"2024-04-10","cited_by_count":7,"area":null},{"id":"2404.09111","title":"Exploring Generative AI for Sim2Real in Driving Data Synthesis","created":"2024-04-14","cited_by_count":7,"area":null},{"id":"2410.15432","title":"MedDiff-FM: A Diffusion-based Foundation Model for Versatile Medical Image Applications","created":"2024-10-20","cited_by_count":7,"area":"diffusion"},{"id":"2212.07352","title":"Bi-Noising Diffusion: Towards Conditional Diffusion Models with Generative Restoration Priors","created":"2022-12-14","cited_by_count":6,"area":"diffusion"},{"id":"2309.12829","title":"Synthetic Boost: Leveraging Synthetic Data for Enhanced Vision-Language Segmentation in Echocardiography","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2311.10868","title":"SDDPM: Speckle Denoising Diffusion Probabilistic Models","created":"2023-11-17","cited_by_count":6,"area":"diffusion"},{"id":"2311.17101","title":"A High-Quality Robust Diffusion Framework for Corrupted Dataset","created":"2023-11-28","cited_by_count":6,"area":null},{"id":"2312.13314","title":"Unlocking Pre-trained Image Backbones for Semantic Image Synthesis","created":"2023-12-20","cited_by_count":6,"area":"diffusion"},{"id":"2403.16954","title":"Isolated Diffusion: Optimizing Multi-Concept Text-to-Image Generation Training-Freely with Isolated Diffusion Guidance","created":"2024-03-25","cited_by_count":6,"area":"diffusion"},{"id":"2403.19880","title":"Vision-Language Synthetic Data Enhances Echocardiography Downstream Tasks","created":"2024-03-28","cited_by_count":6,"area":"synth"},{"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":"2507.03257","title":"LACONIC: A 3D Layout Adapter for Controllable Image Creation","created":"2025-07-04","cited_by_count":6,"area":null},{"id":"2301.11785","title":"Dual Diffusion Architecture for Fisheye Image Rectification: Synthetic-to-Real Generalization","created":"2023-01-26","cited_by_count":5,"area":"diffusion"},{"id":"2308.16071","title":"Semantic Image Synthesis via Class-Adaptive Cross-Attention","created":"2023-08-30","cited_by_count":5,"area":null},{"id":"2312.02984","title":"Diff-GO: Diffusion Goal-Oriented Communications to Achieve Ultra-High Spectrum Efficiency","created":"2023-11-13","cited_by_count":5,"area":"diffusion"},{"id":"2401.03152","title":"Controllable Image Synthesis of Industrial Data Using Stable Diffusion","created":"2024-01-06","cited_by_count":5,"area":"diffusion"},{"id":"2403.17770","title":"CT Synthesis with Conditional Diffusion Models for Abdominal Lymph Node Segmentation","created":"2024-03-26","cited_by_count":5,"area":"diffusion"},{"id":"2411.02334","title":"Communicate Less, Synthesize the Rest: Latency-aware Intent-based Generative Semantic Multicasting with Diffusion Models","created":"2024-11-04","cited_by_count":5,"area":"diffusion"},{"id":"2304.02321","title":"Few-shot Semantic Image Synthesis with Class Affinity Transfer","created":"2023-04-05","cited_by_count":4,"area":null},{"id":"2308.00193","title":"C-DARL: Contrastive diffusion adversarial representation learning for label-free blood vessel segmentation","created":"2023-07-31","cited_by_count":4,"area":null},{"id":"2405.13779","title":"Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2407.08209","title":"Enriching Information and Preserving Semantic Consistency in Expanding Curvilinear Object Segmentation Datasets","created":"2024-07-11","cited_by_count":4,"area":null},{"id":"2408.10207","title":"A Comprehensive Survey on Diffusion Models and Their Applications","created":"2024-07-01","cited_by_count":4,"area":"diffusion"},{"id":"2411.05005","title":"Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models","created":"2024-11-07","cited_by_count":4,"area":"diffusion"},{"id":"2402.02369","title":"M$^3$Face: A Unified Multi-Modal Multilingual Framework for Human Face Generation and Editing","created":"2024-02-04","cited_by_count":3,"area":null},{"id":"2402.14395","title":"Semantic Image Synthesis with Unconditional Generator","created":"2024-02-22","cited_by_count":3,"area":null},{"id":"2403.12743","title":"Controllable Face Synthesis with Semantic Latent Diffusion Models","created":"2024-03-19","cited_by_count":3,"area":"diffusion"},{"id":"2407.02873","title":"Robot Shape and Location Retention in Video Generation Using Diffusion Models","created":"2024-07-03","cited_by_count":3,"area":"diffusion"},{"id":"2407.04800","title":"Segmentation-Free Guidance for Text-to-Image Diffusion Models","created":"2024-06-03","cited_by_count":3,"area":"diffusion"},{"id":"2409.10597","title":"Optimizing Resource Consumption in Diffusion Models through Hallucination Early Detection","created":"2024-09-16","cited_by_count":3,"area":"diffusion"},{"id":"2503.12213","title":"STAY Diffusion: Styled Layout Diffusion Model for Diverse Layout-to-Image Generation","created":"2025-03-15","cited_by_count":3,"area":"diffusion"},{"id":"2305.01138","title":"High-Fidelity Image Synthesis from Pulmonary Nodule Lesion Maps using Semantic Diffusion Model","created":"2023-05-02","cited_by_count":2,"area":"diffusion"},{"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":"2405.14221","title":"Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimization","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2407.15631","title":"A Diffusion Model for Simulation Ready Coronary Anatomy with Morpho-skeletal Control","created":"2024-07-22","cited_by_count":2,"area":"diffusion"},{"id":"2411.07619","title":"Artificial Intelligence for Biomedical Video Generation","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2412.16050","title":"Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac Fluoroscopy","created":"2024-12-20","cited_by_count":2,"area":"diffusion"},{"id":"2309.02478","title":"Enhancing Semantic Communication with Deep Generative Models -- An ICASSP Special Session Overview","created":"2023-09-05","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":"2404.10408","title":"Adversarial Identity Injection for Semantic Face Image Synthesis","created":"2024-04-16","cited_by_count":1,"area":null},{"id":"2407.17882","title":"Artificial Immunofluorescence in a Flash: Rapid Synthetic Imaging from Brightfield Through Residual Diffusion","created":"2024-07-25","cited_by_count":1,"area":"diffusion"},{"id":"2410.04648","title":"AdaptDiff: Cross-Modality Domain Adaptation via Weak Conditional Semantic Diffusion for Retinal Vessel Segmentation","created":"2024-10-06","cited_by_count":1,"area":"diffusion"},{"id":"2410.23962","title":"Image Synthesis with Class-Aware Semantic Diffusion Models for Surgical Scene Segmentation","created":"2024-10-31","cited_by_count":1,"area":"diffusion"},{"id":"2412.17839","title":"LaMI-GO: Latent Mixture Integration for Goal-Oriented Communications Achieving High Spectrum Efficiency","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2601.04588","title":"3D Conditional Image Synthesis of Left Atrial LGE MRI from Composite Semantic Masks","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2605.08851","title":"Geometrically Constrained Stenosis Editing in Coronary Angiography via Entropic Optimal Transport","created":"2026-05-09","cited_by_count":1,"area":null}],"next_cursor":"100"}