{"total":390,"rows":[{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658,"area":"wm"},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590,"area":"wm"},{"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":"2201.04127","title":"HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video","created":"2022-01-11","cited_by_count":483,"area":null},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2303.12688","title":"Pix2Video: Video Editing using Image Diffusion","created":"2023-03-22","cited_by_count":320,"area":"diffusion"},{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314,"area":null},{"id":"2112.14683","title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","created":"2021-12-29","cited_by_count":301,"area":null},{"id":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","cited_by_count":287,"area":null},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255,"area":null},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244,"area":null},{"id":"2203.09481","title":"Diffusion Probabilistic Modeling for Video Generation","created":"2022-03-16","cited_by_count":238,"area":"diffusion"},{"id":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206,"area":"diffusion"},{"id":"2109.08379","title":"PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering","created":"2021-09-17","cited_by_count":203,"area":null},{"id":"2309.03897","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","created":"2023-09-07","cited_by_count":197,"area":null},{"id":"2303.13744","title":"Conditional Image-to-Video Generation with Latent Flow Diffusion Models","created":"2023-03-24","cited_by_count":181,"area":"diffusion"},{"id":"2104.07452","title":"Audio-Driven Emotional Video Portraits","created":"2021-04-15","cited_by_count":180,"area":null},{"id":"2108.03647","title":"AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer","created":"2021-08-08","cited_by_count":178,"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":"2402.03290","title":"InstanceDiffusion: Instance-level Control for Image Generation","created":"2024-02-05","cited_by_count":175,"area":"diffusion"},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172,"area":null},{"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,"area":null},{"id":"2104.15069","title":"A Good Image Generator Is What You Need for High-Resolution Video Synthesis","created":"2021-04-30","cited_by_count":163,"area":null},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154,"area":null},{"id":"2307.00040","title":"DisCo: Disentangled Control for Realistic Human Dance Generation","created":"2023-06-30","cited_by_count":142,"area":null},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136,"area":null},{"id":"2105.01794","title":"Real-time Deep Dynamic Characters","created":"2021-05-04","cited_by_count":133,"area":null},{"id":"2207.07621","title":"MegaPortraits: One-shot Megapixel Neural Head Avatars","created":"2022-07-15","cited_by_count":131,"area":null},{"id":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126,"area":null},{"id":"2104.15060","title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","created":"2021-04-30","cited_by_count":125,"area":null},{"id":"2105.08756","title":"Pathdreamer: A World Model for Indoor Navigation","created":"2021-05-18","cited_by_count":118,"area":"wm"},{"id":"2204.02663","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","created":"2022-04-06","cited_by_count":113,"area":null},{"id":"2106.02019","title":"Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control","created":"2021-06-03","cited_by_count":106,"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":"2503.14492","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","created":"2025-03-18","cited_by_count":106,"area":null},{"id":"2109.02974","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","created":"2021-09-07","cited_by_count":95,"area":null},{"id":"2112.02815","title":"Make It Move: Controllable Image-to-Video Generation with Text Descriptions","created":"2021-12-06","cited_by_count":88,"area":null},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87,"area":null},{"id":"2503.05639","title":"VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control","created":"2025-03-07","cited_by_count":84,"area":null},{"id":"2307.14073","title":"VideoControlNet: A Motion-Guided Video-to-Video Translation Framework by Using Diffusion Model with ControlNet","created":"2023-07-26","cited_by_count":83,"area":"diffusion"},{"id":"2105.10441","title":"Driving-Signal Aware Full-Body Avatars","created":"2021-05-21","cited_by_count":81,"area":null},{"id":"2102.11126","title":"Deepfake Video Detection Using Convolutional Vision Transformer","created":"2021-02-22","cited_by_count":79,"area":null},{"id":"2101.06543","title":"GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving","created":"2021-01-16","cited_by_count":75,"area":null},{"id":"2205.13775","title":"A Survey on Long-Tailed Visual Recognition","created":"2022-05-27","cited_by_count":75,"area":null},{"id":"2105.04619","title":"Enhancing Photorealism Enhancement","created":"2021-05-10","cited_by_count":74,"area":null},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70,"area":null},{"id":"2107.08037","title":"CCVS: Context-aware Controllable Video Synthesis","created":"2021-07-16","cited_by_count":69,"area":null},{"id":"2303.14662","title":"OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Rendering","created":"2023-03-26","cited_by_count":67,"area":null},{"id":"2106.14879","title":"Modeling Clothing as a Separate Layer for an Animatable Human Avatar","created":"2021-06-28","cited_by_count":66,"area":null},{"id":"2101.12195","title":"Playable Video Generation","created":"2021-01-28","cited_by_count":64,"area":null},{"id":"2104.08363","title":"StylePeople: A Generative Model of Fullbody Human Avatars","created":"2021-04-16","cited_by_count":62,"area":null},{"id":"2203.15354","title":"Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production","created":"2022-03-29","cited_by_count":61,"area":null},{"id":"2402.09368","title":"Magic-Me: Identity-Specific Video Customized Diffusion","created":"2024-02-14","cited_by_count":59,"area":null},{"id":"2108.08020","title":"Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates","created":"2021-08-18","cited_by_count":58,"area":null},{"id":"2211.11743","title":"SinFusion: Training Diffusion Models on a Single Image or Video","created":"2022-11-21","cited_by_count":58,"area":"diffusion"},{"id":"2407.21773","title":"RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining","created":"2024-07-31","cited_by_count":56,"area":"ssm"},{"id":"2203.09457","title":"Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image","created":"2022-03-17","cited_by_count":55,"area":null},{"id":"2102.11263","title":"Style and Pose Control for Image Synthesis of Humans from a Single Monocular View","created":"2021-02-22","cited_by_count":53,"area":null},{"id":"2106.04488","title":"Low-Rank Subspaces in GANs","created":"2021-06-08","cited_by_count":53,"area":null},{"id":"2303.09875","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","created":"2023-03-17","cited_by_count":53,"area":null},{"id":"2304.14406","title":"Putting People in Their Place: Affordance-Aware Human Insertion into Scenes","created":"2023-04-27","cited_by_count":53,"area":null},{"id":"2103.06878","title":"Diverse Semantic Image Synthesis via Probability Distribution Modeling","created":"2021-03-11","cited_by_count":49,"area":null},{"id":"2105.04551","title":"Stochastic Image-to-Video Synthesis using cINNs","created":"2021-05-10","cited_by_count":49,"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":"2103.06902","title":"HumanGAN: A Generative Model of Humans Images","created":"2021-03-11","cited_by_count":47,"area":null},{"id":"2301.06281","title":"DPE: Disentanglement of Pose and Expression for General Video Portrait Editing","created":"2023-01-16","cited_by_count":46,"area":null},{"id":"2109.06166","title":"Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN","created":"2021-09-13","cited_by_count":45,"area":null},{"id":"2112.03051","title":"Controllable Animation of Fluid Elements in Still Images","created":"2021-12-06","cited_by_count":45,"area":null},{"id":"2305.11421","title":"PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction","created":"2023-05-19","cited_by_count":44,"area":null},{"id":"2401.03395","title":"Deep Learning-based Image and Video Inpainting: A Survey","created":"2024-01-07","cited_by_count":44,"area":null},{"id":"2206.00923","title":"Modeling Image Composition for Complex Scene Generation","created":"2022-06-02","cited_by_count":43,"area":null},{"id":"2107.02790","title":"iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis","created":"2021-07-06","cited_by_count":42,"area":null},{"id":"2305.03989","title":"LEO: Generative Latent Image Animator for Human Video Synthesis","created":"2023-05-06","cited_by_count":40,"area":null},{"id":"2106.11303","title":"Understanding Object Dynamics for Interactive Image-to-Video Synthesis","created":"2021-06-21","cited_by_count":38,"area":null},{"id":"2212.02469","title":"One-shot Implicit Animatable Avatars with Model-based Priors","created":"2022-12-05","cited_by_count":38,"area":null},{"id":"2307.02106","title":"SoK: Privacy-Preserving Data Synthesis","created":"2023-07-05","cited_by_count":38,"area":null},{"id":"2103.03467","title":"Teachers Do More Than Teach: Compressing Image-to-Image Models","created":"2021-03-05","cited_by_count":37,"area":null},{"id":"2107.12038","title":"Neural Video Compression using GANs for Detail Synthesis and Propagation","created":"2021-07-26","cited_by_count":36,"area":null},{"id":"2109.10595","title":"Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation","created":"2021-09-22","cited_by_count":36,"area":null},{"id":"2104.03507","title":"Progressive Temporal Feature Alignment Network for Video Inpainting","created":"2021-04-08","cited_by_count":35,"area":null},{"id":"2104.10066","title":"EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task","created":"2021-04-16","cited_by_count":34,"area":null},{"id":"2204.05018","title":"Structure-Aware Motion Transfer with Deformable Anchor Model","created":"2022-04-11","cited_by_count":34,"area":null},{"id":"2304.04106","title":"MedGen3D: A Deep Generative Framework for Paired 3D Image and Mask Generation","created":"2023-04-08","cited_by_count":34,"area":null},{"id":"2112.10203","title":"HVTR: Hybrid Volumetric-Textural Rendering for Human Avatars","created":"2021-12-19","cited_by_count":33,"area":null},{"id":"2212.05321","title":"HumanGen: Generating Human Radiance Fields with Explicit Priors","created":"2022-12-10","cited_by_count":33,"area":null},{"id":"2401.10226","title":"Towards Language-Driven Video Inpainting via Multimodal Large Language Models","created":"2024-01-18","cited_by_count":33,"area":"mllm"},{"id":"2211.12824","title":"Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation","created":"2022-11-23","cited_by_count":32,"area":null},{"id":"2403.06351","title":"Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos","created":"2024-03-11","cited_by_count":32,"area":null},{"id":"2403.09069","title":"Dyadic Interaction Modeling for Social Behavior Generation","created":"2024-03-14","cited_by_count":32,"area":null},{"id":"2404.17571","title":"Tunnel Try-on: Excavating Spatial-temporal Tunnels for High-quality Virtual Try-on in Videos","created":"2024-04-26","cited_by_count":32,"area":null},{"id":"2103.03891","title":"LOHO: Latent Optimization of Hairstyles via Orthogonalization","created":"2021-03-05","cited_by_count":30,"area":null},{"id":"2203.01914","title":"Playable Environments: Video Manipulation in Space and Time","created":"2022-03-03","cited_by_count":29,"area":null},{"id":"2307.10008","title":"MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions","created":"2023-07-19","cited_by_count":29,"area":null},{"id":"2104.06637","title":"Decoupled Spatial-Temporal Transformer for Video Inpainting","created":"2021-04-14","cited_by_count":28,"area":null},{"id":"2206.13454","title":"Optimizing Video Prediction via Video Frame Interpolation","created":"2022-06-27","cited_by_count":28,"area":null},{"id":"2212.09102","title":"Face Generation and Editing with StyleGAN: A Survey","created":"2022-12-18","cited_by_count":28,"area":null},{"id":"2406.15735","title":"Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model","created":"2024-06-22","cited_by_count":28,"area":"diffusion"},{"id":"2102.11811","title":"Dynamic Neural Garments","created":"2021-02-23","cited_by_count":27,"area":null},{"id":"2104.14631","title":"Text2Video: Text-driven Talking-head Video Synthesis with Personalized Phoneme-Pose Dictionary","created":"2021-04-29","cited_by_count":27,"area":null},{"id":"2401.10786","title":"Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion","created":"2024-01-19","cited_by_count":27,"area":"diffusion"}],"next_cursor":"100"}