{"list":"other","total":68,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"2302.04264","title":"Nerfstudio: A Modular Framework for Neural Radiance Field Development","created":"2023-02-08","cited_by_count":600},{"id":"2201.04127","title":"HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video","created":"2022-01-11","cited_by_count":483},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474},{"id":"2412.07772","title":"From Slow Bidirectional to Fast Autoregressive Video Diffusion Models","created":"2024-12-10","cited_by_count":433},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2103.16874","title":"VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization","created":"2021-03-31","cited_by_count":287},{"id":"1711.08447","title":"VITON: An Image-based Virtual Try-on Network","created":"2017-11-22","cited_by_count":286},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"id":"1705.09368","title":"Pose Guided Person Image Generation","created":"2017-05-25","cited_by_count":251},{"id":"2403.14773","title":"StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text","created":"2024-03-21","cited_by_count":251},{"id":"2406.19680","title":"MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance","created":"2024-06-28","cited_by_count":198},{"id":"1807.07688","title":"Toward Characteristic-Preserving Image-based Virtual Try-On Network","created":"2018-07-20","cited_by_count":192},{"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":"2304.06025","title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","created":"2023-04-12","cited_by_count":167},{"id":"1801.00055","title":"Deformable GANs for Pose-based Human Image Generation","created":"2017-12-29","cited_by_count":166},{"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":"2206.14180","title":"High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions","created":"2022-06-28","cited_by_count":130},{"id":"1804.04694","title":"A Variational U-Net for Conditional Appearance and Shape Generation","created":"2018-04-12","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":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113},{"id":"2403.05139","title":"Improving Diffusion Models for Authentic Virtual Try-on in the Wild","created":"2024-03-08","cited_by_count":109},{"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":"2504.05298","title":"One-Minute Video Generation with Test-Time Training","created":"2025-04-07","cited_by_count":101},{"id":"1804.07739","title":"Synthesizing Images of Humans in Unseen Poses","created":"2018-04-20","cited_by_count":97},{"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":"2007.02721","title":"Do Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On","created":"2020-07-03","cited_by_count":77},{"id":"2207.09161","title":"Single Stage Virtual Try-on via Deformable Attention Flows","created":"2022-07-19","cited_by_count":65},{"id":"2101.04104","title":"Neural Re-Rendering of Humans from a Single Image","created":"2021-01-11","cited_by_count":59},{"id":"2305.09662","title":"Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation","created":"2023-05-16","cited_by_count":56},{"id":"2011.15128","title":"Animating Pictures with Eulerian Motion Fields","created":"2020-11-30","cited_by_count":55},{"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":"2102.11263","title":"Style and Pose Control for Image Synthesis of Humans from a Single Monocular View","created":"2021-02-22","cited_by_count":53},{"id":"2405.11794","title":"ViViD: Video Virtual Try-on using Diffusion Models","created":"2024-05-20","cited_by_count":42},{"id":"2404.01089","title":"Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On","created":"2024-04-01","cited_by_count":38},{"id":"2404.17571","title":"Tunnel Try-on: Excavating Spatial-temporal Tunnels for High-quality Virtual Try-on in Videos","created":"2024-04-26","cited_by_count":32},{"id":"2406.04542","title":"M&M VTO: Multi-Garment Virtual Try-On and Editing","created":"2024-06-06","cited_by_count":29},{"id":"2403.10783","title":"StableGarment: Garment-Centric Generation via Stable Diffusion","created":"2024-03-16","cited_by_count":27},{"id":"2204.12151","title":"ClothFormer:Taming Video Virtual Try-on in All Module","created":"2022-04-26","cited_by_count":26},{"id":"2501.05763","title":"StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation","created":"2025-01-10","cited_by_count":26},{"id":"2108.07502","title":"MV-TON: Memory-based Video Virtual Try-on network","created":"2021-08-17","cited_by_count":23},{"id":"2407.10625","title":"WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models","created":"2024-07-15","cited_by_count":22},{"id":"2203.15320","title":"Dressing in the Wild by Watching Dance Videos","created":"2022-03-29","cited_by_count":20},{"id":"2411.00225","title":"Fashion-VDM: Video Diffusion Model for Virtual Try-On","created":"2024-10-31","cited_by_count":16},{"id":"2012.10495","title":"ShineOn: Illuminating Design Choices for Practical Video-based Virtual Clothing Try-on","created":"2020-12-18","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":"2403.13951","title":"ACDG-VTON: Accurate and Contained Diffusion Generation for Virtual Try-On","created":"2024-03-20","cited_by_count":2},{"id":"2508.21070","title":"Dress&Dance: Dress up and Dance as You Like It - Technical Preview","created":"2025-08-28","cited_by_count":2}],"next_cursor":null}