{"list":"other","total":56,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"2312.17090","title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","created":"2023-12-28","cited_by_count":503},{"id":"2312.13286","title":"Generative Multimodal Models are In-Context Learners","created":"2023-12-20","cited_by_count":446},{"id":"2305.14720","title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","created":"2023-05-24","cited_by_count":442},{"id":"2206.02779","title":"Blended Latent Diffusion","created":"2022-06-06","cited_by_count":432},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359},{"id":"2311.10089","title":"Emu Edit: Precise Image Editing via Recognition and Generation Tasks","created":"2023-11-16","cited_by_count":324},{"id":"2306.14435","title":"DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing","created":"2023-06-26","cited_by_count":294},{"id":"2501.13918","title":"Improving Video Generation with Human Feedback","created":"2025-01-23","cited_by_count":284},{"id":"2211.12446","title":"EDICT: Exact Diffusion Inversion via Coupled Transformations","created":"2022-11-22","cited_by_count":258},{"id":"2304.06140","title":"An Edit Friendly DDPM Noise Space: Inversion and Manipulations","created":"2023-04-12","cited_by_count":244},{"id":"2306.00980","title":"SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds","created":"2023-06-01","cited_by_count":227},{"id":"2312.06739","title":"SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models","created":"2023-12-11","cited_by_count":177},{"id":"2402.03290","title":"InstanceDiffusion: Instance-level Control for Image Generation","created":"2024-02-05","cited_by_count":175},{"id":"2404.02733","title":"InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation","created":"2024-04-03","cited_by_count":170},{"id":"2212.04489","title":"SINE: SINgle Image Editing with Text-to-Image Diffusion Models","created":"2022-12-08","cited_by_count":159},{"id":"2406.07209","title":"MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance","created":"2024-06-11","cited_by_count":144},{"id":"2312.16272","title":"SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation","created":"2023-12-26","cited_by_count":143},{"id":"2306.04717","title":"AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment","created":"2023-06-07","cited_by_count":142},{"id":"2403.14572","title":"Implicit Style-Content Separation using B-LoRA","created":"2024-03-21","cited_by_count":135},{"id":"2407.05600","title":"GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing","created":"2024-07-08","cited_by_count":133},{"id":"2311.16090","title":"Self-correcting LLM-controlled Diffusion Models","created":"2023-11-27","cited_by_count":113},{"id":"2312.04965","title":"Inversion-Free Image Editing with Natural Language","created":"2023-12-07","cited_by_count":106},{"id":"2402.02583","title":"DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing","created":"2024-02-04","cited_by_count":88},{"id":"2401.08276","title":"AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception","created":"2024-01-16","cited_by_count":65},{"id":"2303.12618","title":"A Perceptual Quality Assessment Exploration for AIGC Images","created":"2023-03-22","cited_by_count":55},{"id":"2402.05195","title":"$\\lambda$-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space","created":"2024-02-07","cited_by_count":51},{"id":"2403.19898","title":"Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpainting","created":"2024-03-29","cited_by_count":40},{"id":"2406.03070","title":"A-Bench: Are LMMs Masters at Evaluating AI-generated Images?","created":"2024-06-05","cited_by_count":39},{"id":"2305.15816","title":"DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion","created":"2023-05-25","cited_by_count":38},{"id":"2307.04684","title":"FreeDrag: Feature Dragging for Reliable Point-based Image Editing","created":"2023-07-10","cited_by_count":29},{"id":"2302.13700","title":"Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech","created":"2023-02-27","cited_by_count":27},{"id":"2401.01117","title":"Q-Refine: A Perceptual Quality Refiner for AI-Generated Image","created":"2024-01-02","cited_by_count":21},{"id":"2208.08880","title":"STTAR: Surgical Tool Tracking using off-the-shelf Augmented Reality Head-Mounted Displays","created":"2022-08-17","cited_by_count":17},{"id":"2409.01322","title":"Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing","created":"2024-09-02","cited_by_count":17},{"id":"2407.10459","title":"DiffStega: Towards Universal Training-Free Coverless Image Steganography with Diffusion Models","created":"2024-07-15","cited_by_count":15},{"id":"2401.09794","title":"Wavelet-Guided Acceleration of Text Inversion in Diffusion-Based Image Editing","created":"2024-01-18","cited_by_count":12},{"id":"2403.00437","title":"LoMOE: Localized Multi-Object Editing via Multi-Diffusion","created":"2024-03-01","cited_by_count":11},{"id":"2410.04738","title":"Diffusion Models in 3D Vision: A Survey","created":"2024-10-07","cited_by_count":11},{"id":"2106.08710","title":"Mobile Augmented Reality: User Interfaces, Frameworks, and Intelligence","created":"2021-06-16","cited_by_count":10},{"id":"2410.11815","title":"SGEdit: Bridging LLM with Text2Image Generative Model for Scene Graph-based Image Editing","created":"2024-10-15","cited_by_count":10},{"id":"2311.10522","title":"Enhancing Object Coherence in Layout-to-Image Synthesis","created":"2023-11-17","cited_by_count":7},{"id":"2402.07677","title":"GBOT: Graph-Based 3D Object Tracking for Augmented Reality-Assisted Assembly Guidance","created":"2024-02-12","cited_by_count":7},{"id":"2403.06452","title":"Text2QR: Harmonizing Aesthetic Customization and Scanning Robustness for Text-Guided QR Code Generation","created":"2024-03-11","cited_by_count":5},{"id":"2402.12660","title":"SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion","created":"2024-02-20","cited_by_count":2},{"id":"2411.19246","title":"Face2QR: A Unified Framework for Aesthetic, Face-Preserving, and Scannable QR Code Generation","created":"2024-11-28","cited_by_count":2}],"next_cursor":null}