{"list":"other","total":102,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"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":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"id":"2403.17888","title":"2D Gaussian Splatting for Geometrically Accurate Radiance Fields","created":"2024-03-26","cited_by_count":1076},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2309.16653","title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","created":"2023-09-28","cited_by_count":843},{"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":"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":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"1703.07332","title":"How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)","created":"2017-03-21","cited_by_count":525},{"id":"2201.04127","title":"HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video","created":"2022-01-11","cited_by_count":483},{"id":"2012.04012","title":"Learning an Animatable Detailed 3D Face Model from In-The-Wild Images","created":"2020-12-07","cited_by_count":477},{"id":"2012.03065","title":"Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction","created":"2020-12-05","cited_by_count":467},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"id":"2401.07519","title":"InstantID: Zero-shot Identity-Preserving Generation in Seconds","created":"2024-01-15","cited_by_count":436},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"2105.02872","title":"Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies","created":"2021-05-06","cited_by_count":361},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2312.02069","title":"GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians","created":"2023-12-04","cited_by_count":260},{"id":"2204.11312","title":"EMOCA: Emotion Driven Monocular Face Capture and Animation","created":"2022-04-24","cited_by_count":255},{"id":"2112.07471","title":"I M Avatar: Implicit Morphable Head Avatars from Videos","created":"2021-12-14","cited_by_count":231},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"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":"2312.02134","title":"GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians","created":"2023-12-04","cited_by_count":191},{"id":"2203.06605","title":"Depth-Aware Generative Adversarial Network for Talking Head Video Generation","created":"2022-03-13","cited_by_count":178},{"id":"2008.08143","title":"How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language","created":"2020-08-18","cited_by_count":173},{"id":"2206.08929","title":"TAVA: Template-free Animatable Volumetric Actors","created":"2022-06-17","cited_by_count":172},{"id":"2403.05087","title":"SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting","created":"2024-03-08","cited_by_count":172},{"id":"2312.02155","title":"GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis","created":"2023-12-04","cited_by_count":170},{"id":"2312.02973","title":"GauHuman: Articulated Gaussian Splatting from Monocular Human Videos","created":"2023-12-05","cited_by_count":168},{"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":"1909.12224","title":"Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis","created":"2019-09-26","cited_by_count":161},{"id":"2405.04233","title":"Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models","created":"2024-05-07","cited_by_count":160},{"id":"2008.09062","title":"Monocular Expressive Body Regression through Body-Driven Attention","created":"2020-08-20","cited_by_count":155},{"id":"2112.01524","title":"GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras","created":"2021-12-02","cited_by_count":153},{"id":"2112.01517","title":"Efficient Neural Radiance Fields for Interactive Free-viewpoint Video","created":"2021-12-02","cited_by_count":150},{"id":"2307.00040","title":"DisCo: Disentangled Control for Realistic Human Dance Generation","created":"2023-06-30","cited_by_count":142},{"id":"2311.16043","title":"Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracing","created":"2023-11-27","cited_by_count":142},{"id":"2210.10036","title":"ARAH: Animatable Volume Rendering of Articulated Human SDFs","created":"2022-10-18","cited_by_count":139},{"id":"2212.10550","title":"InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds","created":"2022-12-20","cited_by_count":138},{"id":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","cited_by_count":137},{"id":"2207.07621","title":"MegaPortraits: One-shot Megapixel Neural Head Avatars","created":"2022-07-15","cited_by_count":131},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130},{"id":"2312.03704","title":"Relightable Gaussian Codec Avatars","created":"2023-12-06","cited_by_count":127},{"id":"2206.06481","title":"RigNeRF: Fully Controllable Neural 3D Portraits","created":"2022-06-13","cited_by_count":126},{"id":"2311.16099","title":"GART: Gaussian Articulated Template Models","created":"2023-11-27","cited_by_count":121},{"id":"2311.12052","title":"MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion","created":"2023-11-18","cited_by_count":117},{"id":"2403.15704","title":"Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections","created":"2024-03-23","cited_by_count":117},{"id":"2312.02214","title":"FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding","created":"2023-12-03","cited_by_count":108},{"id":"2410.07971","title":"Generalizable and Animatable Gaussian Head Avatar","created":"2024-10-10","cited_by_count":97},{"id":"2407.21686","title":"Expressive Whole-Body 3D Gaussian Avatar","created":"2024-07-31","cited_by_count":89},{"id":"2404.04104","title":"SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis","created":"2024-04-05","cited_by_count":84},{"id":"2011.11534","title":"Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation","created":"2020-11-23","cited_by_count":81},{"id":"2112.02753","title":"MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image","created":"2021-12-06","cited_by_count":74},{"id":"2401.10215","title":"GPAvatar: Generalizable and Precise Head Avatar from Image(s)","created":"2024-01-18","cited_by_count":74},{"id":"2403.13570","title":"Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer","created":"2024-03-20","cited_by_count":64},{"id":"2312.11461","title":"GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning","created":"2023-12-18","cited_by_count":63},{"id":"1810.11610","title":"Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis","created":"2018-10-27","cited_by_count":59},{"id":"2407.07532","title":"Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation","created":"2024-07-10","cited_by_count":59},{"id":"2311.18729","title":"Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data","created":"2023-11-30","cited_by_count":55},{"id":"2412.14963","title":"IDOL: Instant Photorealistic 3D Human Creation from a Single Image","created":"2024-12-19","cited_by_count":55},{"id":"2406.12459","title":"HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors","created":"2024-06-18","cited_by_count":54},{"id":"2401.04468","title":"MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation","created":"2024-01-09","cited_by_count":48},{"id":"2407.09646","title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","created":"2024-07-12","cited_by_count":45},{"id":"2212.02469","title":"One-shot Implicit Animatable Avatars with Model-based Priors","created":"2022-12-05","cited_by_count":38},{"id":"2309.17128","title":"HAvatar: High-fidelity Head Avatar via Facial Model Conditioned Neural Radiance Field","created":"2023-09-29","cited_by_count":37},{"id":"2311.16482","title":"Animatable 3D Gaussian: Fast and High-Quality Reconstruction of Multiple Human Avatars","created":"2023-11-27","cited_by_count":30},{"id":"2406.06050","title":"Generalizable Human Gaussians from Single-View Image","created":"2024-06-10","cited_by_count":29},{"id":"2503.08224","title":"HRAvatar: High-Quality and Relightable Gaussian Head Avatar","created":"2025-03-11","cited_by_count":25},{"id":"2304.09502","title":"Sampling is Matter: Point-guided 3D Human Mesh Reconstruction","created":"2023-04-19","cited_by_count":24},{"id":"2412.08331","title":"SLGaussian: Fast Language Gaussian Splatting in Sparse Views","created":"2024-12-11","cited_by_count":18},{"id":"1802.01822","title":"Geometry-Contrastive GAN for Facial Expression Transfer","created":"2018-02-06","cited_by_count":16},{"id":"1911.10672","title":"GAC-GAN: A General Method for Appearance-Controllable Human Video Motion Transfer","created":"2019-11-25","cited_by_count":14},{"id":"2003.13510","title":"Human Motion Transfer with 3D Constraints and Detail Enhancement","created":"2020-03-30","cited_by_count":14},{"id":"2502.10982","title":"TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction","created":"2025-02-16","cited_by_count":14},{"id":"1401.5823","title":"Collaborative Regression","created":"2014-01-22","cited_by_count":9},{"id":"2310.06275","title":"High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field","created":"2023-10-10","cited_by_count":5},{"id":"2305.02981","title":"Adversarially-Guided Portrait Matting","created":"2023-05-04","cited_by_count":4}],"next_cursor":"100"}