{"total":229,"rows":[{"id":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76,"area":null},{"id":"2504.02436","title":"SkyReels-A2: Compose Anything in Video Diffusion Transformers","created":"2025-04-03","cited_by_count":73,"area":"diffusion"},{"id":"2502.06145","title":"Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance","created":"2025-02-10","cited_by_count":61,"area":"diffusion"},{"id":"2503.10625","title":"LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds","created":"2025-03-13","cited_by_count":61,"area":null},{"id":"2412.14963","title":"IDOL: Instant Photorealistic 3D Human Creation from a Single Image","created":"2024-12-19","cited_by_count":55,"area":null},{"id":"2502.20220","title":"Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars","created":"2025-02-27","cited_by_count":53,"area":null},{"id":"2502.04847","title":"HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation","created":"2025-02-07","cited_by_count":39,"area":"diffusion"},{"id":"2412.02684","title":"AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction","created":"2024-12-03","cited_by_count":36,"area":null},{"id":"2501.09782","title":"SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation","created":"2025-01-16","cited_by_count":32,"area":null},{"id":"2503.01610","title":"Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior","created":"2025-03-03","cited_by_count":31,"area":null},{"id":"2503.21761","title":"Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video","created":"2025-03-27","cited_by_count":29,"area":null},{"id":"2412.09606","title":"Feat2GS: Probing Visual Foundation Models with Gaussian Splatting","created":"2024-12-12","cited_by_count":27,"area":null},{"id":"2507.14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2501.10928","title":"Generative Physical AI in Vision: A Survey","created":"2025-01-19","cited_by_count":24,"area":null},{"id":"2409.10141","title":"PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing","created":"2024-09-16","cited_by_count":23,"area":null},{"id":"2502.12782","title":"VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation","created":"2025-02-18","cited_by_count":23,"area":null},{"id":"2503.08507","title":"Referring to Any Person","created":"2025-03-11","cited_by_count":21,"area":null},{"id":"2511.00940","title":"URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model","created":"2025-11-02","cited_by_count":21,"area":"wm"},{"id":"2502.07785","title":"Pippo: High-Resolution Multi-View Humans from a Single Image","created":"2025-02-11","cited_by_count":20,"area":null},{"id":"2505.00615","title":"Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction","created":"2025-05-01","cited_by_count":20,"area":null},{"id":"2504.11732","title":"EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos","created":"2025-04-16","cited_by_count":19,"area":null},{"id":"2510.16258","title":"Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset","created":"2025-10-17","cited_by_count":19,"area":null},{"id":"2502.20387","title":"InsTaG: Learning Personalized 3D Talking Head from Few-Second Video","created":"2025-02-27","cited_by_count":18,"area":null},{"id":"2507.13344","title":"Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models","created":"2025-07-17","cited_by_count":17,"area":"diffusion"},{"id":"2412.21206","title":"PERSE: Personalized 3D Generative Avatars from A Single Portrait","created":"2024-12-30","cited_by_count":15,"area":null},{"id":"2503.20822","title":"Synthetic Video Enhances Physical Fidelity in Video Synthesis","created":"2025-03-26","cited_by_count":15,"area":null},{"id":"2508.13104","title":"Precise Action-to-Video Generation Through Visual Action Prompts","created":"2025-08-18","cited_by_count":15,"area":null},{"id":"2504.04708","title":"SapiensID: Foundation for Human Recognition","created":"2025-04-07","cited_by_count":14,"area":null},{"id":"2504.04956","title":"REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning","created":"2025-04-07","cited_by_count":14,"area":"diffusion"},{"id":"2607.09024","title":"Video Generation Models are General-Purpose Vision Learners","created":"2026-07-10","cited_by_count":14,"area":null},{"id":"2412.01383","title":"Second FRCSyn-onGoing: Winning Solutions and Post-Challenge Analysis to Improve Face Recognition with Synthetic Data","created":"2024-12-02","cited_by_count":13,"area":null},{"id":"2504.04126","title":"Multi-identity Human Image Animation with Structural Video Diffusion","created":"2025-04-05","cited_by_count":13,"area":"diffusion"},{"id":"2504.12186","title":"CoMotion: Concurrent Multi-person 3D Motion","created":"2025-04-16","cited_by_count":13,"area":null},{"id":"2504.21308","title":"AGHI-QA: A Subjective-Aligned Dataset and Metric for AI-Generated Human Images","created":"2025-04-30","cited_by_count":13,"area":null},{"id":"2508.09383","title":"X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion Latents","created":"2025-08-12","cited_by_count":13,"area":null},{"id":"2508.09973","title":"PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image","created":"2025-08-13","cited_by_count":13,"area":null},{"id":"2502.08556","title":"Human-Centric Foundation Models: Perception, Generation and Agentic Modeling","created":"2025-02-12","cited_by_count":12,"area":"agents"},{"id":"2504.06982","title":"SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets","created":"2025-04-09","cited_by_count":12,"area":null},{"id":"2504.08353","title":"Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates","created":"2025-04-11","cited_by_count":12,"area":null},{"id":"2506.17206","title":"DreamCube: 3D Panorama Generation via Multi-plane Synchronization","created":"2025-06-20","cited_by_count":12,"area":null},{"id":"2508.15767","title":"ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling","created":"2025-08-21","cited_by_count":12,"area":null},{"id":"2412.15171","title":"SqueezeMe: Mobile-Ready Distillation of Gaussian Full-Body Avatars","created":"2024-12-19","cited_by_count":11,"area":null},{"id":"2503.20644","title":"MMGen: Unified Multi-modal Image Generation and Understanding in One Go","created":"2025-03-26","cited_by_count":11,"area":"diffusion"},{"id":"2507.15365","title":"DAViD: Data-efficient and Accurate Vision Models from Synthetic Data","created":"2025-07-21","cited_by_count":11,"area":null},{"id":"2504.00665","title":"Monocular and Generalizable Gaussian Talking Head Animation","created":"2025-04-01","cited_by_count":10,"area":null},{"id":"2505.01838","title":"MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitization","created":"2025-05-03","cited_by_count":9,"area":null},{"id":"2508.05091","title":"PoseGen: In-Context LoRA Finetuning for Pose-Controllable Long Human Video Generation","created":"2025-08-07","cited_by_count":9,"area":null},{"id":"2508.20210","title":"InfinityHuman: Towards Long-Term Audio-Driven Human","created":"2025-08-27","cited_by_count":9,"area":null},{"id":"2602.01661","title":"From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2412.02690","title":"FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation","created":"2024-12-03","cited_by_count":8,"area":null},{"id":"2502.02307","title":"UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training","created":"2025-02-04","cited_by_count":8,"area":null},{"id":"2507.23597","title":"MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction","created":"2025-07-31","cited_by_count":8,"area":"diffusion"},{"id":"2508.04825","title":"Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off","created":"2025-08-06","cited_by_count":8,"area":"diffusion"},{"id":"2501.04631","title":"Disentangled Clothed Avatar Generation with Layered Representation","created":"2025-01-08","cited_by_count":7,"area":null},{"id":"2503.15406","title":"Visual Persona: Foundation Model for Full-Body Human Customization","created":"2025-03-19","cited_by_count":7,"area":"diffusion"},{"id":"2504.18152","title":"ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video Understanding","created":"2025-04-25","cited_by_count":7,"area":"mllm"},{"id":"2508.09137","title":"HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis","created":"2025-08-12","cited_by_count":7,"area":null},{"id":"2509.18924","title":"Audio-Driven Universal Gaussian Head Avatars","created":"2025-09-23","cited_by_count":7,"area":null},{"id":"2604.03305","title":"HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis","created":"2026-03-31","cited_by_count":7,"area":null},{"id":"2411.18624","title":"GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data","created":"2024-11-27","cited_by_count":6,"area":"diffusion"},{"id":"2502.01045","title":"WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstruction","created":"2025-02-03","cited_by_count":6,"area":null},{"id":"2503.08678","title":"GarmentCrafter: Progressive Novel View Synthesis for Single-View 3D Garment Reconstruction and Editing","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2505.19742","title":"HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2512.03000","title":"DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling","created":"2025-12-02","cited_by_count":5,"area":"wm"},{"id":"2603.25892","title":"THFM: A Unified Video Foundation Model for 4D Human Perception and Beyond","created":"2026-03-26","cited_by_count":5,"area":"diffusion"},{"id":"2605.09258","title":"Monocular Biomechanical Tracking of Fingers with Inverse Kinematics to Foundation Models","created":"2026-05-10","cited_by_count":5,"area":null},{"id":"2411.16289","title":"Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2503.00861","title":"Zero-Shot Head Swapping in Real-World Scenarios","created":"2025-03-02","cited_by_count":4,"area":null},{"id":"2503.19207","title":"FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2504.16315","title":"SignX: Continuous Sign Recognition in Compact Pose-Rich Latent Space","created":"2025-04-22","cited_by_count":4,"area":null},{"id":"2506.03119","title":"Controllable Human-centric Keyframe Interpolation with Generative Prior","created":"2025-06-03","cited_by_count":4,"area":"diffusion"},{"id":"2510.07190","title":"MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis","created":"2025-10-08","cited_by_count":4,"area":"diffusion"},{"id":"2512.01340","title":"EvalTalker: Learning to Evaluate Real-Portrait-Driven Multi-Subject Talking Humans","created":"2025-12-01","cited_by_count":4,"area":null},{"id":"2512.09646","title":"VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification","created":"2025-12-10","cited_by_count":4,"area":null},{"id":"2601.13837","title":"FastGHA: Generalized Few-Shot 3D Gaussian Head Avatars with Real-Time Animation","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2603.28760","title":"SHOW3D: Capturing Scenes of 3D Hands and Objects in the Wild","created":"2026-03-30","cited_by_count":4,"area":null},{"id":"2604.21681","title":"Sapiens2","created":"2026-04-23","cited_by_count":4,"area":null},{"id":"2503.09040","title":"Motion Blender Gaussian Splatting for Dynamic Scene Reconstruction","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2503.15996","title":"Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models","created":"2025-03-20","cited_by_count":3,"area":"diffusion"},{"id":"2504.17414","title":"3DV-TON: Textured 3D-Guided Consistent Video Try-on via Diffusion Models","created":"2025-04-24","cited_by_count":3,"area":"diffusion"},{"id":"2506.01802","title":"UMA: Ultra-detailed Human Avatars via Multi-level Surface Alignment","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2506.21270","title":"Video Virtual Try-on with Conditional Diffusion Transformer Inpainter","created":"2025-06-26","cited_by_count":3,"area":"diffusion"},{"id":"2507.02803","title":"HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars","created":"2025-07-03","cited_by_count":3,"area":null},{"id":"2508.04505","title":"MonoCloth: Reconstruction and Animation of Cloth-Decoupled Human Avatars from Monocular Videos","created":"2025-08-06","cited_by_count":3,"area":null},{"id":"2508.07905","title":"Generative Video Matting","created":"2025-08-11","cited_by_count":3,"area":null},{"id":"2509.24980","title":"SDPose: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation","created":"2025-09-29","cited_by_count":3,"area":"diffusion"},{"id":"2510.03532","title":"Efficient Surgical Robotic Instrument Pose Reconstruction in Real World Conditions Using Unified Feature Detection","created":"2025-10-03","cited_by_count":3,"area":null},{"id":"2510.11650","title":"InfiniHuman: Infinite 3D Human Creation with Precise Control","created":"2025-10-13","cited_by_count":3,"area":null},{"id":"2511.22553","title":"Bringing Your Portrait to 3D Presence","created":"2025-11-27","cited_by_count":3,"area":null},{"id":"2603.14772","title":"Zero-Shot Reconstruction of Animatable 3D Avatars with Cloth Dynamics from a Single Image","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2603.21332","title":"EmoTaG: Emotion-Aware Talking Head Synthesis on Gaussian Splatting with Few-Shot Personalization","created":"2026-03-22","cited_by_count":3,"area":null},{"id":"2604.02320","title":"Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining","created":"2026-04-02","cited_by_count":3,"area":null},{"id":"2604.20715","title":"GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers","created":"2026-04-22","cited_by_count":3,"area":"diffusion"},{"id":"2606.31249","title":"Rethinking the Role of Feature Engineering and Learning Strategies in Few-Shot Hidden Emotion Recognition","created":"2026-06-30","cited_by_count":3,"area":null},{"id":"2412.01562","title":"Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2501.06680","title":"Application of Vision-Language Model to Pedestrians Behavior and Scene Understanding in Autonomous Driving","created":"2025-01-12","cited_by_count":2,"area":"mllm"},{"id":"2503.08201","title":"Scale-Aware Pre-Training for Human-Centric Visual Perception: Enabling Lightweight and Generalizable Models","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2504.15835","title":"Text-based Animatable 3D Avatars with Morphable Model Alignment","created":"2025-04-22","cited_by_count":2,"area":"diffusion"},{"id":"2505.20582","title":"Total-Editing: Head Avatar with Editable Appearance, Motion, and Lighting","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2505.23085","title":"GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion","created":"2025-05-29","cited_by_count":2,"area":"diffusion"}],"next_cursor":"100"}