{"total":525,"rows":[{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487,"area":null},{"id":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288,"area":null},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255,"area":null},{"id":"2112.07471","title":"I M Avatar: Implicit Morphable Head Avatars from Videos","created":"2021-12-14","cited_by_count":231,"area":null},{"id":"2202.04053","title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","created":"2022-02-08","cited_by_count":230,"area":"lr"},{"id":"2112.08867","title":"GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation","created":"2021-12-16","cited_by_count":216,"area":null},{"id":"2112.01554","title":"Neural Head Avatars from Monocular RGB Videos","created":"2021-12-02","cited_by_count":213,"area":null},{"id":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210,"area":null},{"id":"2306.07280","title":"Controlling Text-to-Image Diffusion by Orthogonal Finetuning","created":"2023-06-12","cited_by_count":208,"area":"diffusion"},{"id":"2109.06590","title":"High-Fidelity GAN Inversion for Image Attribute Editing","created":"2021-09-14","cited_by_count":197,"area":null},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175,"area":null},{"id":"2204.06607","title":"Towards Metrical Reconstruction of Human Faces","created":"2022-04-13","cited_by_count":166,"area":null},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153,"area":null},{"id":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","cited_by_count":137,"area":null},{"id":"2207.07621","title":"MegaPortraits: One-shot Megapixel Neural Head Avatars","created":"2022-07-15","cited_by_count":131,"area":null},{"id":"2201.07131","title":"Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection","created":"2022-01-18","cited_by_count":130,"area":null},{"id":"2206.08343","title":"Realistic One-shot Mesh-based Head Avatars","created":"2022-06-16","cited_by_count":119,"area":null},{"id":"2211.14758","title":"VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild","created":"2022-11-27","cited_by_count":106,"area":null},{"id":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103,"area":null},{"id":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98,"area":null},{"id":"2401.08503","title":"Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis","created":"2024-01-16","cited_by_count":97,"area":null},{"id":"2410.07971","title":"Generalizable and Animatable Gaussian Head Avatar","created":"2024-10-10","cited_by_count":97,"area":null},{"id":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95,"area":null},{"id":"2211.14506","title":"Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis","created":"2022-11-26","cited_by_count":93,"area":null},{"id":"2105.04714","title":"Sample and Computation Redistribution for Efficient Face Detection","created":"2021-05-10","cited_by_count":89,"area":null},{"id":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85,"area":null},{"id":"2404.04104","title":"SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis","created":"2024-04-05","cited_by_count":84,"area":null},{"id":"2211.12368","title":"Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition","created":"2022-11-22","cited_by_count":81,"area":null},{"id":"2103.10094","title":"KoDF: A Large-scale Korean DeepFake Detection Dataset","created":"2021-03-18","cited_by_count":80,"area":null},{"id":"2212.13344","title":"DiffFace: Diffusion-based Face Swapping with Facial Guidance","created":"2022-12-27","cited_by_count":77,"area":"diffusion"},{"id":"2401.10215","title":"GPAvatar: Generalizable and Precise Head Avatar from Image(s)","created":"2024-01-18","cited_by_count":74,"area":null},{"id":"2206.07255","title":"GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds","created":"2022-06-15","cited_by_count":73,"area":null},{"id":"2204.02776","title":"3D face reconstruction with dense landmarks","created":"2022-04-06","cited_by_count":70,"area":null},{"id":"2304.05097","title":"One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field","created":"2023-04-11","cited_by_count":68,"area":null},{"id":"2106.11895","title":"A Latent Transformer for Disentangled Face Editing in Images and Videos","created":"2021-06-22","cited_by_count":67,"area":null},{"id":"2307.10854","title":"BlendFace: Re-designing Identity Encoders for Face-Swapping","created":"2023-07-20","cited_by_count":66,"area":null},{"id":"2404.01030","title":"Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation","created":"2024-04-01","cited_by_count":66,"area":null},{"id":"2208.00847","title":"MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild","created":"2022-08-01","cited_by_count":65,"area":null},{"id":"2305.02310","title":"Real-Time Radiance Fields for Single-Image Portrait View Synthesis","created":"2023-05-03","cited_by_count":64,"area":null},{"id":"2307.09906","title":"Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation","created":"2023-07-19","cited_by_count":61,"area":null},{"id":"2104.14222","title":"Privacy-Preserving Portrait Matting","created":"2021-04-29","cited_by_count":60,"area":null},{"id":"2105.06464","title":"DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision","created":"2021-05-13","cited_by_count":59,"area":null},{"id":"2412.09262","title":"LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision","created":"2024-12-12","cited_by_count":56,"area":"diffusion"},{"id":"2212.04248","title":"Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors","created":"2022-12-07","cited_by_count":55,"area":"diffusion"},{"id":"2311.18729","title":"Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data","created":"2023-11-30","cited_by_count":55,"area":null},{"id":"2412.12093","title":"CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models","created":"2024-12-16","cited_by_count":52,"area":"diffusion"},{"id":"2207.11094","title":"Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videos","created":"2022-07-22","cited_by_count":50,"area":null},{"id":"2308.09716","title":"Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization","created":"2023-08-18","cited_by_count":49,"area":"diffusion"},{"id":"2103.15432","title":"Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracing","created":"2021-03-29","cited_by_count":48,"area":null},{"id":"2304.03199","title":"Face Animation with an Attribute-Guided Diffusion Model","created":"2023-04-06","cited_by_count":48,"area":"diffusion"},{"id":"2212.06246","title":"Jointly Learning Visual and Auditory Speech Representations from Raw Data","created":"2022-12-12","cited_by_count":47,"area":null},{"id":"2210.10473","title":"FaceDancer: Pose- and Occlusion-Aware High Fidelity Face Swapping","created":"2022-10-19","cited_by_count":44,"area":null},{"id":"2309.06441","title":"Learning Disentangled Avatars with Hybrid 3D Representations","created":"2023-09-12","cited_by_count":44,"area":null},{"id":"2306.05872","title":"Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction","created":"2023-06-09","cited_by_count":43,"area":null},{"id":"2502.17796","title":"LAM: Large Avatar Model for One-shot Animatable Gaussian Head","created":"2025-02-25","cited_by_count":43,"area":null},{"id":"2509.16630","title":"Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation","created":"2025-09-20","cited_by_count":43,"area":null},{"id":"2304.10168","title":"High-Fidelity and Freely Controllable Talking Head Video Generation","created":"2023-04-20","cited_by_count":42,"area":null},{"id":"2406.07867","title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation","created":"2024-06-12","cited_by_count":41,"area":null},{"id":"2210.08160","title":"Learning Dual Memory Dictionaries for Blind Face Restoration","created":"2022-10-15","cited_by_count":40,"area":null},{"id":"2412.01064","title":"FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait","created":"2024-12-02","cited_by_count":40,"area":"diffusion"},{"id":"2211.13874","title":"FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction","created":"2022-11-25","cited_by_count":39,"area":null},{"id":"2308.11509","title":"SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation","created":"2023-08-22","cited_by_count":39,"area":null},{"id":"2309.07125","title":"Text-Guided Generation and Editing of Compositional 3D Avatars","created":"2023-09-13","cited_by_count":39,"area":null},{"id":"2310.17519","title":"FLARE: Fast Learning of Animatable and Relightable Mesh Avatars","created":"2023-10-26","cited_by_count":39,"area":null},{"id":"2107.12351","title":"NeLF: Neural Light-transport Field for Portrait View Synthesis and Relighting","created":"2021-07-26","cited_by_count":38,"area":null},{"id":"2403.14852","title":"KeyPoint Relative Position Encoding for Face Recognition","created":"2024-03-21","cited_by_count":38,"area":null},{"id":"2111.01082","title":"FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstruction","created":"2021-11-01","cited_by_count":36,"area":null},{"id":"2207.10387","title":"Pose for Everything: Towards Category-Agnostic Pose Estimation","created":"2022-07-21","cited_by_count":36,"area":null},{"id":"2101.05356","title":"Practical Face Reconstruction via Differentiable Ray Tracing","created":"2021-01-13","cited_by_count":35,"area":null},{"id":"2205.02058","title":"SVTS: Scalable Video-to-Speech Synthesis","created":"2022-05-04","cited_by_count":35,"area":null},{"id":"2301.10939","title":"Affective Faces for Goal-Driven Dyadic Communication","created":"2023-01-26","cited_by_count":35,"area":null},{"id":"2312.03029","title":"HHAvatar: Gaussian Head Avatar with Dynamic Hairs","created":"2023-12-05","cited_by_count":35,"area":null},{"id":"2109.05721","title":"ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment","created":"2021-09-13","cited_by_count":34,"area":null},{"id":"2108.10378","title":"Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras","created":"2021-08-23","cited_by_count":33,"area":null},{"id":"2202.12972","title":"FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment","created":"2022-02-25","cited_by_count":33,"area":null},{"id":"2312.04651","title":"VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment","created":"2023-12-07","cited_by_count":33,"area":null},{"id":"2101.03749","title":"Deep Learning-based Face Super-Resolution: A Survey","created":"2021-01-11","cited_by_count":32,"area":null},{"id":"2104.14557","title":"Learned Spatial Representations for Few-shot Talking-Head Synthesis","created":"2021-04-29","cited_by_count":32,"area":null},{"id":"2104.03493","title":"Riggable 3D Face Reconstruction via In-Network Optimization","created":"2021-04-08","cited_by_count":31,"area":null},{"id":"2107.04174","title":"EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments","created":"2021-07-09","cited_by_count":31,"area":null},{"id":"2204.03688","title":"DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image","created":"2022-04-07","cited_by_count":31,"area":null},{"id":"2208.10808","title":"Towards Accurate Facial Landmark Detection via Cascaded Transformers","created":"2022-08-23","cited_by_count":31,"area":null},{"id":"2303.05955","title":"Neuron Structure Modeling for Generalizable Remote Physiological Measurement","created":"2023-03-10","cited_by_count":31,"area":null},{"id":"2101.09866","title":"Supervision by Registration and Triangulation for Landmark Detection","created":"2021-01-25","cited_by_count":30,"area":null},{"id":"2103.03891","title":"LOHO: Latent Optimization of Hairstyles via Orthogonalization","created":"2021-03-05","cited_by_count":30,"area":null},{"id":"2404.05680","title":"SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representation","created":"2024-04-08","cited_by_count":30,"area":null},{"id":"2112.00585","title":"Neural Emotion Director: Speech-preserving semantic control of facial expressions in \"in-the-wild\" videos","created":"2021-12-01","cited_by_count":28,"area":null},{"id":"2507.23143","title":"X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention","created":"2025-07-30","cited_by_count":28,"area":null},{"id":"2106.03021","title":"SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction","created":"2021-06-06","cited_by_count":27,"area":null},{"id":"2110.09772","title":"Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry","created":"2021-10-19","cited_by_count":27,"area":null},{"id":"2202.00046","title":"Finding Directions in GAN's Latent Space for Neural Face Reenactment","created":"2022-01-31","cited_by_count":27,"area":null},{"id":"2202.10673","title":"Seeing is Living? Rethinking the Security of Facial Liveness Verification in the Deepfake Era","created":"2022-02-22","cited_by_count":27,"area":null},{"id":"2505.21448","title":"OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers","created":"2025-05-27","cited_by_count":27,"area":"diffusion"},{"id":"2103.16554","title":"Pre-training strategies and datasets for facial representation learning","created":"2021-03-30","cited_by_count":26,"area":null},{"id":"2109.00471","title":"Sparse to Dense Motion Transfer for Face Image Animation","created":"2021-09-01","cited_by_count":25,"area":null},{"id":"2209.01383","title":"Training Strategies for Improved Lip-reading","created":"2022-09-03","cited_by_count":25,"area":"distill"},{"id":"2305.19012","title":"StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation","created":"2023-05-30","cited_by_count":25,"area":"diffusion"},{"id":"2407.10487","title":"Lite2Relight: 3D-aware Single Image Portrait Relighting","created":"2024-07-15","cited_by_count":25,"area":null},{"id":"2107.07695","title":"Self-supervised Representation Learning Framework for Remote Physiological Measurement Using Spatiotemporal Augmentation Loss","created":"2021-07-16","cited_by_count":24,"area":null},{"id":"2111.01048","title":"MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation","created":"2021-11-01","cited_by_count":24,"area":null}],"next_cursor":"100"}