{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"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":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"2305.10431","title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention","created":"2023-05-17","cited_by_count":313},{"id":"2103.16874","title":"VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization","created":"2021-03-31","cited_by_count":287},{"id":"2307.10816","title":"BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion","created":"2023-07-20","cited_by_count":282},{"id":"2303.14389","title":"MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer","created":"2023-03-25","cited_by_count":262},{"id":"1705.09368","title":"Pose Guided Person Image Generation","created":"2017-05-25","cited_by_count":251},{"id":"2203.06026","title":"The Role of ImageNet Classes in Fr\\'echet Inception Distance","created":"2022-03-11","cited_by_count":213},{"id":"2312.01725","title":"StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On","created":"2023-12-04","cited_by_count":175},{"id":"1801.00055","title":"Deformable GANs for Pose-based Human Image Generation","created":"2017-12-29","cited_by_count":166},{"id":"2306.05427","title":"Grounded Text-to-Image Synthesis with Attention Refocusing","created":"2023-06-08","cited_by_count":164},{"id":"2204.08532","title":"Dress Code: High-Resolution Multi-Category Virtual Try-On","created":"2022-04-18","cited_by_count":162},{"id":"2305.13501","title":"LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On","created":"2023-05-22","cited_by_count":152},{"id":"2403.01779","title":"OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on","created":"2024-03-04","cited_by_count":151},{"id":"2003.12267","title":"Controllable Person Image Synthesis with Attribute-Decomposed GAN","created":"2020-03-27","cited_by_count":150},{"id":"2003.05863","title":"Towards Photo-Realistic Virtual Try-On by Adaptively Generating$\\leftrightarrow$Preserving Image Content","created":"2020-03-12","cited_by_count":149},{"id":"2103.04559","title":"Parser-Free Virtual Try-on via Distilling Appearance Flows","created":"2021-03-08","cited_by_count":143},{"id":"2306.08276","title":"TryOnDiffusion: A Tale of Two UNets","created":"2023-06-14","cited_by_count":141},{"id":"1904.03349","title":"Progressive Pose Attention Transfer for Person Image Generation","created":"2019-04-06","cited_by_count":138},{"id":"2206.14180","title":"High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions","created":"2022-06-28","cited_by_count":130},{"id":"2308.06101","title":"Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow","created":"2023-08-11","cited_by_count":124},{"id":"2303.13756","title":"GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning","created":"2023-03-24","cited_by_count":120},{"id":"2403.05139","title":"Improving Diffusion Models for Authentic Virtual Try-on in the Wild","created":"2024-03-08","cited_by_count":109},{"id":"1903.11326","title":"Dense Intrinsic Appearance Flow for Human Pose Transfer","created":"2019-03-27","cited_by_count":104},{"id":"2211.12500","title":"Person Image Synthesis via Denoising Diffusion Model","created":"2022-11-22","cited_by_count":104},{"id":"2310.06313","title":"Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models","created":"2023-10-10","cited_by_count":104},{"id":"2407.15886","title":"CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models","created":"2024-07-21","cited_by_count":102},{"id":"2003.00696","title":"Deep Image Spatial Transformation for Person Image Generation","created":"2020-03-02","cited_by_count":100},{"id":"2204.01046","title":"Style-Based Global Appearance Flow for Virtual Try-On","created":"2022-04-03","cited_by_count":88},{"id":"2007.09278","title":"XingGAN for Person Image Generation","created":"2020-07-17","cited_by_count":81},{"id":"2203.02910","title":"Exploring Dual-task Correlation for Pose Guided Person Image Generation","created":"2022-03-06","cited_by_count":68},{"id":"2103.04023","title":"PISE: Person Image Synthesis and Editing with Decoupled GAN","created":"2021-03-06","cited_by_count":62},{"id":"2103.09479","title":"Disentangled Cycle Consistency for Highly-realistic Virtual Try-On","created":"2021-03-17","cited_by_count":62},{"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":"2204.06160","title":"Neural Texture Extraction and Distribution for Controllable Person Image Synthesis","created":"2022-04-13","cited_by_count":55},{"id":"2404.02747","title":"Faster Diffusion via Temporal Attention Decomposition","created":"2024-04-03","cited_by_count":54},{"id":"2311.18405","title":"CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model","created":"2023-11-30","cited_by_count":48},{"id":"2402.18078","title":"Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis","created":"2024-02-28","cited_by_count":48},{"id":"2208.00712","title":"Cross Attention Based Style Distribution for Controllable Person Image Synthesis","created":"2022-08-01","cited_by_count":45},{"id":"2404.01089","title":"Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On","created":"2024-04-01","cited_by_count":38},{"id":"2311.16094","title":"Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images","created":"2023-11-27","cited_by_count":34},{"id":"2406.04542","title":"M&M VTO: Multi-Garment Virtual Try-On and Editing","created":"2024-06-06","cited_by_count":29},{"id":"2312.15861","title":"Towards Squeezing-Averse Virtual Try-On via Sequential Deformation","created":"2023-12-26","cited_by_count":18},{"id":"2103.11521","title":"Conditional Frechet Inception Distance","created":"2021-03-21","cited_by_count":16},{"id":"2407.16224","title":"OutfitAnyone: Ultra-high Quality Virtual Try-On for Any Clothing and Any Person","created":"2024-07-23","cited_by_count":16},{"id":"2110.05458","title":"Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistency","created":"2021-10-11","cited_by_count":15},{"id":"2409.08258","title":"Improving Virtual Try-On with Garment-focused Diffusion Models","created":"2024-09-12","cited_by_count":15},{"id":"2312.04534","title":"PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns","created":"2023-12-07","cited_by_count":14},{"id":"2407.15111","title":"D$^4$-VTON: Dynamic Semantics Disentangling for Differential Diffusion based Virtual Try-On","created":"2024-07-21","cited_by_count":14},{"id":"2312.00210","title":"DREAM: Diffusion Rectification and Estimation-Adaptive Models","created":"2023-11-30","cited_by_count":12},{"id":"2402.01516","title":"Cross-view Masked Diffusion Transformers for Person Image Synthesis","created":"2024-02-02","cited_by_count":12},{"id":"2303.17688","title":"Learning Garment DensePose for Robust Warping in Virtual Try-On","created":"2023-03-30","cited_by_count":5}],"next_cursor":null}