{"list":"other","total":58,"rows":[{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2112.07945","title":"Efficient Geometry-aware 3D Generative Adversarial Networks","created":"2021-12-15","cited_by_count":1205},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2011.12100","title":"GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields","created":"2020-11-24","cited_by_count":785},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2012.15838","title":"Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans","created":"2020-12-31","cited_by_count":634},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"2110.08985","title":"StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis","created":"2021-10-18","cited_by_count":477},{"id":"2401.07519","title":"InstantID: Zero-shot Identity-Preserving Generation in Seconds","created":"2024-01-15","cited_by_count":436},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"2105.02872","title":"Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies","created":"2021-05-06","cited_by_count":361},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2112.11427","title":"StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation","created":"2021-12-21","cited_by_count":289},{"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":"2102.06199","title":"A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose","created":"2021-02-11","cited_by_count":233},{"id":"2112.05637","title":"HeadNeRF: A Real-time NeRF-based Parametric Head Model","created":"2021-12-10","cited_by_count":228},{"id":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210},{"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":"2104.03110","title":"Neural Articulated Radiance Field","created":"2021-04-07","cited_by_count":196},{"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":"2305.06356","title":"HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion","created":"2023-05-10","cited_by_count":161},{"id":"2110.09788","title":"CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis","created":"2021-10-19","cited_by_count":149},{"id":"2307.00040","title":"DisCo: Disentangled Control for Realistic Human Dance Generation","created":"2023-06-30","cited_by_count":142},{"id":"1904.03349","title":"Progressive Pose Attention Transfer for Person Image Generation","created":"2019-04-06","cited_by_count":138},{"id":"1910.09139","title":"DwNet: Dense warp-based network for pose-guided human video generation","created":"2019-10-21","cited_by_count":115},{"id":"2502.02492","title":"VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models","created":"2025-02-04","cited_by_count":113},{"id":"2106.13629","title":"Animatable Neural Radiance Fields from Monocular RGB Videos","created":"2021-06-25","cited_by_count":109},{"id":"2211.12500","title":"Person Image Synthesis via Denoising Diffusion Model","created":"2022-11-22","cited_by_count":104},{"id":"2405.20674","title":"4Diffusion: Multi-view Video Diffusion Model for 4D Generation","created":"2024-05-31","cited_by_count":104},{"id":"1712.02621","title":"Disentangled Person Image Generation","created":"2017-12-07","cited_by_count":98},{"id":"1809.01995","title":"Dense Pose Transfer","created":"2018-09-06","cited_by_count":83},{"id":"2008.06872","title":"SMPLpix: Neural Avatars from 3D Human Models","created":"2020-08-16","cited_by_count":69},{"id":"2503.10625","title":"LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds","created":"2025-03-13","cited_by_count":61},{"id":"2101.04104","title":"Neural Re-Rendering of Humans from a Single Image","created":"2021-01-11","cited_by_count":59},{"id":"1809.10280","title":"Unsupervised Person Image Synthesis in Arbitrary Poses","created":"2018-09-27","cited_by_count":55},{"id":"2012.12890","title":"ANR: Articulated Neural Rendering for Virtual Avatars","created":"2020-12-23","cited_by_count":55},{"id":"2401.04468","title":"MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation","created":"2024-01-09","cited_by_count":48},{"id":"2412.02684","title":"AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction","created":"2024-12-03","cited_by_count":36},{"id":"2112.10203","title":"HVTR: Hybrid Volumetric-Textural Rendering for Human Avatars","created":"2021-12-19","cited_by_count":33},{"id":"1808.06847","title":"Deep Video-Based Performance Cloning","created":"2018-08-21","cited_by_count":32},{"id":"2504.03072","title":"How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Models","created":"2025-04-03","cited_by_count":32},{"id":"2307.07754","title":"Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer","created":"2023-07-15","cited_by_count":25},{"id":"2407.08428","title":"A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights","created":"2024-07-11","cited_by_count":25},{"id":"2111.12685","title":"EgoRenderer: Rendering Human Avatars from Egocentric Camera Images","created":"2021-11-24","cited_by_count":13},{"id":"1711.11453","title":"Improving Video Generation for Multi-functional Applications","created":"2017-11-30","cited_by_count":9},{"id":"2404.01225","title":"SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering","created":"2024-04-01","cited_by_count":9}],"next_cursor":null}