{"list":"other","total":62,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2201.11793","title":"Denoising Diffusion Restoration Models","created":"2022-01-27","cited_by_count":963},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2305.08995","title":"Denoising Diffusion Models for Plug-and-Play Image Restoration","created":"2023-05-15","cited_by_count":340},{"id":"2411.15098","title":"OminiControl: Minimal and Universal Control for Diffusion Transformer","created":"2024-11-22","cited_by_count":340},{"id":"2306.00986","title":"Diffusion Self-Guidance for Controllable Image Generation","created":"2023-06-01","cited_by_count":305},{"id":"2306.14435","title":"DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing","created":"2023-06-26","cited_by_count":294},{"id":"1711.08447","title":"VITON: An Image-based Virtual Try-on Network","created":"2017-11-22","cited_by_count":286},{"id":"1705.09368","title":"Pose Guided Person Image Generation","created":"2017-05-25","cited_by_count":251},{"id":"2305.10973","title":"Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold","created":"2023-05-18","cited_by_count":219},{"id":"2203.15270","title":"MAT: Mask-Aware Transformer for Large Hole Image Inpainting","created":"2022-03-29","cited_by_count":218},{"id":"2312.02133","title":"Style Aligned Image Generation via Shared Attention","created":"2023-12-04","cited_by_count":216},{"id":"2306.04675","title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","created":"2023-06-07","cited_by_count":205},{"id":"2304.01247","title":"Generative Diffusion Prior for Unified Image Restoration and Enhancement","created":"2023-04-03","cited_by_count":199},{"id":"2307.02421","title":"DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models","created":"2023-07-05","cited_by_count":195},{"id":"1807.07688","title":"Toward Characteristic-Preserving Image-based Virtual Try-On Network","created":"2018-07-20","cited_by_count":192},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185},{"id":"2312.01597","title":"SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference","created":"2023-12-04","cited_by_count":170},{"id":"1801.00055","title":"Deformable GANs for Pose-based Human Image Generation","created":"2017-12-29","cited_by_count":166},{"id":"1904.03349","title":"Progressive Pose Attention Transfer for Person Image Generation","created":"2019-04-06","cited_by_count":138},{"id":"1606.03798","title":"Deep Image Homography Estimation","created":"2016-06-13","cited_by_count":136},{"id":"2311.03335","title":"Cross-Image Attention for Zero-Shot Appearance Transfer","created":"2023-11-06","cited_by_count":136},{"id":"2403.03431","title":"Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing","created":"2024-03-06","cited_by_count":135},{"id":"2402.03286","title":"Training-Free Consistent Text-to-Image Generation","created":"2024-02-05","cited_by_count":125},{"id":"2312.10113","title":"Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation","created":"2023-12-15","cited_by_count":62},{"id":"2104.07021","title":"Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing","created":"2021-04-14","cited_by_count":54},{"id":"2312.02150","title":"Readout Guidance: Learning Control from Diffusion Features","created":"2023-12-04","cited_by_count":52},{"id":"2404.01050","title":"Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation","created":"2024-04-01","cited_by_count":51},{"id":"2401.01702","title":"Image Sculpting: Precise Object Editing with 3D Geometry Control","created":"2024-01-02","cited_by_count":45},{"id":"2401.18085","title":"Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators","created":"2024-01-31","cited_by_count":39},{"id":"2403.15382","title":"DragAPart: Learning a Part-Level Motion Prior for Articulated Objects","created":"2024-03-22","cited_by_count":32},{"id":"2407.18247","title":"RegionDrag: Fast Region-Based Image Editing with Diffusion Models","created":"2024-07-25","cited_by_count":32},{"id":"2409.08857","title":"InstantDrag: Improving Interactivity in Drag-based Image Editing","created":"2024-09-13","cited_by_count":31},{"id":"2403.04437","title":"StableDrag: Stable Dragging for Point-based Image Editing","created":"2024-03-07","cited_by_count":28},{"id":"2403.14487","title":"DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing","created":"2024-03-21","cited_by_count":20},{"id":"2404.16029","title":"Editable Image Elements for Controllable Synthesis","created":"2024-04-24","cited_by_count":13},{"id":"2404.07178","title":"Move Anything with Layered Scene Diffusion","created":"2024-04-10","cited_by_count":12},{"id":"2103.11622","title":"Progressive and Aligned Pose Attention Transfer for Person Image Generation","created":"2021-03-22","cited_by_count":7}],"next_cursor":null}