{"total":99,"rows":[{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611,"area":"diffusion"},{"id":"2202.00273","title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","created":"2022-02-01","cited_by_count":492,"area":null},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375,"area":"diffusion"},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327,"area":"diffusion"},{"id":"2310.17596","title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","created":"2023-10-26","cited_by_count":327,"area":"offlinerl"},{"id":"2212.08420","title":"Fake it till you make it: Learning transferable representations from synthetic ImageNet clones","created":"2022-12-16","cited_by_count":172,"area":"diffusion"},{"id":"2303.11681","title":"DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models","created":"2023-03-21","cited_by_count":162,"area":"diffusion"},{"id":"2308.06160","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","created":"2023-08-11","cited_by_count":123,"area":"diffusion"},{"id":"2309.14303","title":"Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation","created":"2023-09-25","cited_by_count":112,"area":null},{"id":"2305.16289","title":"Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation","created":"2023-05-25","cited_by_count":100,"area":null},{"id":"2301.05221","title":"Open-vocabulary Object Segmentation with Diffusion Models","created":"2023-01-12","cited_by_count":82,"area":"diffusion"},{"id":"2204.07513","title":"Synthesizing Informative Training Samples with GAN","created":"2022-04-15","cited_by_count":77,"area":null},{"id":"2304.09787","title":"NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models","created":"2023-04-19","cited_by_count":76,"area":"diffusion"},{"id":"2211.13976","title":"Expanding Small-Scale Datasets with Guided Imagination","created":"2022-11-25","cited_by_count":62,"area":null},{"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":"2303.09813","title":"DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery","created":"2023-03-17","cited_by_count":54,"area":"diffusion"},{"id":"2401.11739","title":"EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models","created":"2024-01-22","cited_by_count":43,"area":"diffusion"},{"id":"2403.16605","title":"SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation","created":"2024-03-25","cited_by_count":41,"area":"diffusion"},{"id":"2405.14785","title":"EditWorld: Simulating World Dynamics for Instruction-Following Image Editing","created":"2024-05-23","cited_by_count":38,"area":"diffusion"},{"id":"2307.07487","title":"DreamTeacher: Pretraining Image Backbones with Deep Generative Models","created":"2023-07-14","cited_by_count":37,"area":null},{"id":"2310.10402","title":"Real-Fake: Effective Training Data Synthesis Through Distribution Matching","created":"2023-10-16","cited_by_count":36,"area":null},{"id":"2309.13042","title":"MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation","created":"2023-09-22","cited_by_count":35,"area":"diffusion"},{"id":"2306.07200","title":"Fill-Up: Balancing Long-Tailed Data with Generative Models","created":"2023-06-12","cited_by_count":34,"area":null},{"id":"2311.17921","title":"Do text-free diffusion models learn discriminative visual representations?","created":"2023-11-29","cited_by_count":33,"area":"diffusion"},{"id":"2308.03977","title":"PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning","created":"2023-08-08","cited_by_count":31,"area":null},{"id":"2305.15407","title":"Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets","created":"2023-05-24","cited_by_count":27,"area":"mllm"},{"id":"2410.14987","title":"SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning","created":"2024-10-19","cited_by_count":27,"area":null},{"id":"2312.09231","title":"Reliability in Semantic Segmentation: Can We Use Synthetic Data?","created":"2023-12-14","cited_by_count":24,"area":null},{"id":"2403.12803","title":"DreamDA: Generative Data Augmentation with Diffusion Models","created":"2024-03-19","cited_by_count":24,"area":"diffusion"},{"id":"2312.02253","title":"Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2403.06741","title":"Distribution-Aware Data Expansion with Diffusion Models","created":"2024-03-11","cited_by_count":20,"area":"diffusion"},{"id":"2311.03355","title":"SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis","created":"2023-11-06","cited_by_count":18,"area":null},{"id":"2403.07750","title":"Synth$^2$: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings","created":"2024-03-12","cited_by_count":18,"area":"mllm"},{"id":"2304.03526","title":"Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field","created":"2023-04-07","cited_by_count":15,"area":null},{"id":"2405.10185","title":"DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data","created":"2024-05-16","cited_by_count":15,"area":null},{"id":"2409.14066","title":"KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data","created":"2024-09-21","cited_by_count":15,"area":"mllm"},{"id":"2304.10253","title":"Image retrieval outperforms diffusion models on data augmentation","created":"2023-04-20","cited_by_count":14,"area":"diffusion"},{"id":"2403.12852","title":"Generative Enhancement for 3D Medical Images","created":"2024-03-19","cited_by_count":14,"area":"diffusion"},{"id":"2302.02108","title":"Knowledge Distillation in Vision Transformers: A Critical Review","created":"2023-02-04","cited_by_count":13,"area":"distill"},{"id":"2310.01830","title":"AI-Generated Images as Data Source: The Dawn of Synthetic Era","created":"2023-10-03","cited_by_count":13,"area":null},{"id":"2403.06168","title":"DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation","created":"2024-03-10","cited_by_count":13,"area":null},{"id":"2407.05352","title":"Exploring Phrase-Level Grounding with Text-to-Image Diffusion Model","created":"2024-07-07","cited_by_count":13,"area":"diffusion"},{"id":"2404.00292","title":"LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion","created":"2024-03-30","cited_by_count":12,"area":"rag"},{"id":"2305.10118","title":"Bridging the Gap: Enhancing the Utility of Synthetic Data via Post-Processing Techniques","created":"2023-05-17","cited_by_count":11,"area":null},{"id":"2406.02435","title":"Generative Active Learning for Long-tailed Instance Segmentation","created":"2024-06-04","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":"2212.12645","title":"HandsOff: Labeled Dataset Generation With No Additional Human Annotations","created":"2022-12-24","cited_by_count":9,"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":"2312.02548","title":"GeNIe: Generative Hard Negative Images Through Diffusion","created":"2023-12-05","cited_by_count":8,"area":"diffusion"},{"id":"2303.09677","title":"Instance-Conditioned GAN Data Augmentation for Representation Learning","created":"2023-03-16","cited_by_count":7,"area":null},{"id":"2208.10913","title":"Deepfake: Definitions, Performance Metrics and Standards, Datasets and Benchmarks, and a Meta-Review","created":"2022-08-21","cited_by_count":6,"area":null},{"id":"2308.06739","title":"Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks","created":"2023-08-13","cited_by_count":6,"area":"diffusion"},{"id":"2410.09865","title":"SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data","created":"2024-10-13","cited_by_count":6,"area":"synth"},{"id":"2503.09938","title":"PanoGen++: Domain-Adapted Text-Guided Panoramic Environment Generation for Vision-and-Language Navigation","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2510.15783","title":"ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection","created":"2025-10-17","cited_by_count":6,"area":"diffusion"},{"id":"2208.14958","title":"A Realism Metric for Generated LiDAR Point Clouds","created":"2022-08-31","cited_by_count":5,"area":null},{"id":"2301.02160","title":"ANNA: Abstractive Text-to-Image Synthesis with Filtered News Captions","created":"2023-01-05","cited_by_count":5,"area":null},{"id":"2311.17121","title":"ScribbleGen: Generative Data Augmentation Improves Scribble-supervised Semantic Segmentation","created":"2023-11-28","cited_by_count":5,"area":"diffusion"},{"id":"2407.07627","title":"Synthetic to Authentic: Transferring Realism to 3D Face Renderings for Boosting Face Recognition","created":"2024-07-10","cited_by_count":5,"area":null},{"id":"2408.00106","title":"WAS: Dataset and Methods for Artistic Text Segmentation","created":"2024-07-31","cited_by_count":5,"area":null},{"id":"2412.10339","title":"Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2507.19808","title":"SeeDiff: Off-the-Shelf Seeded Mask Generation from Diffusion Models","created":"2025-07-26","cited_by_count":5,"area":"diffusion"},{"id":"2309.01369","title":"Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation","created":"2023-09-04","cited_by_count":4,"area":"diffusion"},{"id":"2403.11263","title":"Stylized Face Sketch Extraction via Generative Prior with Limited Data","created":"2024-03-17","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":"2503.12563","title":"Diffusion on Graph: Augmentation of Graph Structure for Node Classification","created":"2025-03-16","cited_by_count":4,"area":"diffusion"},{"id":"2504.02180","title":"Foreground Focus: Enhancing Coherence and Fidelity in Camouflaged Image Generation","created":"2025-04-02","cited_by_count":4,"area":null},{"id":"2504.08473","title":"Cut-and-Splat: Leveraging Gaussian Splatting for Synthetic Data Generation","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2512.13014","title":"JoDiffusion: Jointly Diffusing Image with Pixel-Level Annotations for Semantic Segmentation Promotion","created":"2025-12-15","cited_by_count":4,"area":"diffusion"},{"id":"2312.17505","title":"Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion","created":"2023-12-29","cited_by_count":3,"area":"diffusion"},{"id":"2502.01980","title":"Generative Data Mining with Longtail-Guided Diffusion","created":"2025-02-04","cited_by_count":3,"area":"diffusion"},{"id":"2506.04676","title":"Gen-n-Val: Agentic Image Data Generation and Validation","created":"2025-06-05","cited_by_count":3,"area":"agents"},{"id":"2603.23906","title":"GenMask: Adapting DiT for Segmentation via Direct Mask Generation","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2312.05953","title":"RadImageGAN -- A Multi-modal Dataset-Scale Generative AI for Medical Imaging","created":"2023-12-10","cited_by_count":2,"area":null},{"id":"2505.19495","title":"The Role of Video Generation in Enhancing Data-Limited Action Understanding","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.02294","title":"Improving Knowledge Distillation Under Unknown Covariate Shift Through Confidence-Guided Data Augmentation","created":"2025-06-02","cited_by_count":2,"area":"distill"},{"id":"2511.03928","title":"SynQuE: Estimating Synthetic Dataset Quality Without Annotations","created":"2025-11-06","cited_by_count":2,"area":"synth"},{"id":"2203.11173","title":"Interpreting Class Conditional GANs with Channel Awareness","created":"2022-03-21","cited_by_count":1,"area":null},{"id":"2305.17207","title":"Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image Models","created":"2023-05-26","cited_by_count":1,"area":null},{"id":"2309.00248","title":"DiffuGen: Adaptable Approach for Generating Labeled Image Datasets using Stable Diffusion Models","created":"2023-09-01","cited_by_count":1,"area":"diffusion"},{"id":"2311.12063","title":"DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2312.15247","title":"Prompt-Propose-Verify: A Reliable Hand-Object-Interaction Data Generation Framework using Foundational Models","created":"2023-12-23","cited_by_count":1,"area":"diffusion"},{"id":"2406.14510","title":"V-LASIK: Consistent Glasses-Removal from Videos Using Synthetic Data","created":"2024-06-20","cited_by_count":1,"area":"diffusion"},{"id":"2502.17056","title":"SpecDM: Hyperspectral Dataset Synthesis with Pixel-level Semantic Annotations","created":"2025-02-24","cited_by_count":1,"area":"diffusion"},{"id":"2503.17095","title":"FFaceNeRF: Few-shot Face Editing in Neural Radiance Fields","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2504.05456","title":"Generative Adversarial Networks with Limited Data: A Survey and Benchmarking","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2505.17695","title":"SynRES: Towards Referring Expression Segmentation in the Wild via Synthetic Data","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2512.22974","title":"RealCamo: Boosting Real Camouflage Synthesis with Layout Controls and Textual-Visual Guidance","created":"2025-12-28","cited_by_count":1,"area":null},{"id":"2207.02712","title":"Histopathology DatasetGAN: Synthesizing Large-Resolution Histopathology Datasets","created":"2022-07-06","cited_by_count":0,"area":null},{"id":"2401.15282","title":"GEM: Boost Simple Network for Glass Surface Segmentation via Segment Anything Model and Data Synthesis","created":"2024-01-27","cited_by_count":0,"area":"diffusion"},{"id":"2404.10141","title":"ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2503.22172","title":"CA-LoRA: Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2508.06032","title":"Learning 3D Texture-Aware Representations for Parsing Diverse Human Clothing and Body Parts","created":"2025-08-08","cited_by_count":0,"area":"diffusion"},{"id":"2510.05722","title":"Data Factory with Minimal Human Effort Using VLMs","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2602.00583","title":"MAUGen: A Unified Diffusion Approach for Multi-Identity Facial Expression and AU Label Generation","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2603.19575","title":"MagicSeg: Open-World Segmentation Pretraining via Counterfactural Diffusion-Based Auto-Generation","created":"2026-03-20","cited_by_count":0,"area":"diffusion"},{"id":"2604.13841","title":"DiffMagicFace: Identity Consistent Facial Editing of Real Videos","created":"2026-04-15","cited_by_count":0,"area":"diffusion"},{"id":"2605.19289","title":"What Makes Synthetic Data Effective in Image Segmentation","created":"2026-05-19","cited_by_count":0,"area":"diffusion"},{"id":"2609.19966","title":"Beyond the Foreground: FOV-Aware Polyp Image Synthesis via Lesion-Guided Adaptive Mucosal Context Propagation","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}