{"list":"other","total":82,"rows":[{"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":"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":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"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":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"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":"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":"2301.11093","title":"Simple diffusion: End-to-end diffusion for high resolution images","created":"2023-01-26","cited_by_count":422},{"id":"2111.05849","title":"Advances in Neural Rendering","created":"2021-11-10","cited_by_count":365},{"id":"2305.08891","title":"Common Diffusion Noise Schedules and Sample Steps are Flawed","created":"2023-05-15","cited_by_count":310},{"id":"1905.08233","title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","created":"2019-05-20","cited_by_count":284},{"id":"2103.01954","title":"Mixture of Volumetric Primitives for Efficient Neural Rendering","created":"2021-03-02","cited_by_count":277},{"id":"2312.02069","title":"GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians","created":"2023-12-04","cited_by_count":260},{"id":"2402.17485","title":"EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions","created":"2024-02-27","cited_by_count":235},{"id":"2112.07471","title":"I M Avatar: Implicit Morphable Head Avatars from Videos","created":"2021-12-14","cited_by_count":231},{"id":"2112.01554","title":"Neural Head Avatars from Monocular RGB Videos","created":"2021-12-02","cited_by_count":213},{"id":"2109.08379","title":"PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering","created":"2021-09-17","cited_by_count":203},{"id":"2003.13989","title":"FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction","created":"2020-03-31","cited_by_count":196},{"id":"2305.03027","title":"NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads","created":"2023-05-04","cited_by_count":194},{"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":"2404.10667","title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","created":"2024-04-16","cited_by_count":187},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185},{"id":"2212.08377","title":"PointAvatar: Deformable Point-based Head Avatars from Videos","created":"2022-12-16","cited_by_count":184},{"id":"2301.02379","title":"CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior","created":"2023-01-06","cited_by_count":184},{"id":"2205.03409","title":"VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution","created":"2022-05-06","cited_by_count":176},{"id":"2406.01900","title":"Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation","created":"2024-06-04","cited_by_count":174},{"id":"2403.05087","title":"SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting","created":"2024-03-08","cited_by_count":172},{"id":"2203.04036","title":"StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN","created":"2022-03-08","cited_by_count":169},{"id":"2204.06607","title":"Towards Metrical Reconstruction of Human Faces","created":"2022-04-13","cited_by_count":166},{"id":"2006.10214","title":"MediaPipe Hands: On-device Real-time Hand Tracking","created":"2020-06-18","cited_by_count":161},{"id":"2211.12499","title":"Instant Volumetric Head Avatars","created":"2022-11-22","cited_by_count":159},{"id":"2108.11515","title":"Robust High-Resolution Video Matting with Temporal Guidance","created":"2021-08-25","cited_by_count":137},{"id":"2207.07621","title":"MegaPortraits: One-shot Megapixel Neural Head Avatars","created":"2022-07-15","cited_by_count":131},{"id":"2104.04638","title":"Pixel Codec Avatars","created":"2021-04-09","cited_by_count":127},{"id":"2312.03704","title":"Relightable Gaussian Codec Avatars","created":"2023-12-06","cited_by_count":127},{"id":"2206.08343","title":"Realistic One-shot Mesh-based Head Avatars","created":"2022-06-16","cited_by_count":119},{"id":"2008.10174","title":"Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars","created":"2020-08-24","cited_by_count":118},{"id":"2405.17414","title":"Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control","created":"2024-05-27","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":"2004.12000","title":"Neural Head Reenactment with Latent Pose Descriptors","created":"2020-04-24","cited_by_count":106},{"id":"2012.08261","title":"HeadGAN: One-shot Neural Head Synthesis and Editing","created":"2020-12-15","cited_by_count":105},{"id":"2401.08503","title":"Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis","created":"2024-01-16","cited_by_count":97},{"id":"2410.07971","title":"Generalizable and Animatable Gaussian Head Avatar","created":"2024-10-10","cited_by_count":97},{"id":"2112.02308","title":"MoFaNeRF: Morphable Facial Neural Radiance Field","created":"2021-12-04","cited_by_count":94},{"id":"2403.15931","title":"X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention","created":"2024-03-23","cited_by_count":91},{"id":"2111.09996","title":"LOLNeRF: Learn from One Look","created":"2021-11-19","cited_by_count":84},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77},{"id":"2304.06711","title":"DiffusionRig: Learning Personalized Priors for Facial Appearance Editing","created":"2023-04-13","cited_by_count":75},{"id":"2212.02761","title":"Learning Neural Parametric Head Models","created":"2022-12-06","cited_by_count":73},{"id":"2212.08062","title":"MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation","created":"2022-12-15","cited_by_count":69},{"id":"2303.14662","title":"OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Rendering","created":"2023-03-26","cited_by_count":67},{"id":"2203.03339","title":"L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments","created":"2022-03-07","cited_by_count":65},{"id":"2305.02310","title":"Real-Time Radiance Fields for Single-Image Portrait View Synthesis","created":"2023-05-03","cited_by_count":64},{"id":"2403.13570","title":"Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer","created":"2024-03-20","cited_by_count":64},{"id":"2311.18729","title":"Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data","created":"2023-11-30","cited_by_count":55},{"id":"2307.03441","title":"NOFA: NeRF-based One-shot Facial Avatar Reconstruction","created":"2023-07-07","cited_by_count":53},{"id":"2305.13353","title":"RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars","created":"2023-05-22","cited_by_count":45},{"id":"2403.07764","title":"Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model","created":"2024-03-12","cited_by_count":45},{"id":"2304.01436","title":"Learning Personalized High Quality Volumetric Head Avatars from Monocular RGB Videos","created":"2023-04-04","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":"2004.11598","title":"Deep 3D Portrait from a Single Image","created":"2020-04-24","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":"2312.06740","title":"MonoNPHM: Dynamic Head Reconstruction from Monocular Videos","created":"2023-12-11","cited_by_count":35},{"id":"2312.04651","title":"VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment","created":"2023-12-07","cited_by_count":33},{"id":"2212.06384","title":"PV3D: A 3D Generative Model for Portrait Video Generation","created":"2022-12-13","cited_by_count":23},{"id":"2404.09819","title":"3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow","created":"2024-04-15","cited_by_count":20},{"id":"2410.16395","title":"Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions","created":"2024-10-21","cited_by_count":18},{"id":"2404.00636","title":"Learning to Generate Conditional Tri-plane for 3D-aware Expression Controllable Portrait Animation","created":"2024-03-31","cited_by_count":15},{"id":"2406.13272","title":"AniFaceDiff: Animating Stylized Avatars via Parametric Conditioned Diffusion Models","created":"2024-06-19","cited_by_count":1}],"next_cursor":null}