{"list":"other","total":68,"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":"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"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":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"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":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"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":"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":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"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":"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":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210},{"id":"2407.03168","title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","created":"2024-07-03","cited_by_count":206},{"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":"2212.08377","title":"PointAvatar: Deformable Point-based Head Avatars from Videos","created":"2022-12-16","cited_by_count":184},{"id":"2203.06605","title":"Depth-Aware Generative Adversarial Network for Talking Head Video Generation","created":"2022-03-13","cited_by_count":178},{"id":"1905.06817","title":"Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision","created":"2019-05-16","cited_by_count":176},{"id":"2403.05087","title":"SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting","created":"2024-03-08","cited_by_count":172},{"id":"2211.12499","title":"Instant Volumetric Head Avatars","created":"2022-11-22","cited_by_count":159},{"id":"2011.11961","title":"MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition","created":"2020-11-24","cited_by_count":127},{"id":"2312.03704","title":"Relightable Gaussian Codec Avatars","created":"2023-12-06","cited_by_count":127},{"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":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104},{"id":"2312.04558","title":"MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatar","created":"2023-12-07","cited_by_count":89},{"id":"2210.01868","title":"Capturing and Animation of Body and Clothing from Monocular Video","created":"2022-10-04","cited_by_count":83},{"id":"2312.07409","title":"DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing","created":"2023-12-12","cited_by_count":67},{"id":"2205.08535","title":"AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars","created":"2022-05-17","cited_by_count":55},{"id":"2305.00121","title":"Learning Locally Editable Virtual Humans","created":"2023-04-28","cited_by_count":54},{"id":"2305.01190","title":"LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatar","created":"2023-05-02","cited_by_count":50},{"id":"2312.04410","title":"Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models","created":"2023-12-07","cited_by_count":49},{"id":"2210.01794","title":"Implicit Warping for Animation with Image Sets","created":"2022-10-04","cited_by_count":45},{"id":"2309.06441","title":"Learning Disentangled Avatars with Hybrid 3D Representations","created":"2023-09-12","cited_by_count":44},{"id":"2408.06019","title":"HeadGAP: Few-Shot 3D Head Avatar via Generalizable Gaussian Priors","created":"2024-08-12","cited_by_count":44},{"id":"2311.18635","title":"DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars","created":"2023-11-30","cited_by_count":42},{"id":"2307.12560","title":"Interpolating between Images with Diffusion Models","created":"2023-07-24","cited_by_count":38},{"id":"2405.20851","title":"MegActor: Harness the Power of Raw Video for Vivid Portrait Animation","created":"2024-05-31","cited_by_count":28},{"id":"2302.04868","title":"MEGANE: Morphable Eyeglass and Avatar Network","created":"2023-02-09","cited_by_count":24},{"id":"2408.14211","title":"MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement","created":"2024-08-26","cited_by_count":24},{"id":"2401.12979","title":"GALA: Generating Animatable Layered Assets from a Single Scan","created":"2024-01-23","cited_by_count":21},{"id":"2305.14345","title":"NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects","created":"2023-05-23","cited_by_count":17},{"id":"2404.14410","title":"Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses","created":"2024-04-22","cited_by_count":17},{"id":"2409.09605","title":"DreamMover: Leveraging the Prior of Diffusion Models for Image Interpolation with Large Motion","created":"2024-09-15","cited_by_count":16},{"id":"2408.13413","title":"TVG: A Training-free Transition Video Generation Method with Diffusion Models","created":"2024-08-24","cited_by_count":15},{"id":"2403.08840","title":"NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation","created":"2024-03-13","cited_by_count":13},{"id":"2408.14975","title":"MegActor-$\\Sigma$: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer","created":"2024-08-27","cited_by_count":13},{"id":"2402.10636","title":"PEGASUS: Personalized Generative 3D Avatars with Composable Attributes","created":"2024-02-16","cited_by_count":7}],"next_cursor":null}