{"total":100,"rows":[{"id":"2403.13802","title":"ZigMa: A DiT-style Zigzag Mamba Diffusion Model","created":"2024-03-20","cited_by_count":84,"area":"diffusion"},{"id":"2303.11579","title":"Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation","created":"2023-03-21","cited_by_count":82,"area":null},{"id":"2401.08570","title":"RoHM: Robust Human Motion Reconstruction via Diffusion","created":"2024-01-16","cited_by_count":48,"area":null},{"id":"2504.16064","title":"Boosting Generative Image Modeling via Joint Image-Feature Synthesis","created":"2025-04-22","cited_by_count":45,"area":"diffusion"},{"id":"2404.00658","title":"KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation","created":"2024-03-31","cited_by_count":34,"area":null},{"id":"2308.16682","title":"DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion","created":"2023-08-31","cited_by_count":31,"area":null},{"id":"2311.16495","title":"Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement","created":"2023-11-28","cited_by_count":31,"area":null},{"id":"2404.05218","title":"Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning","created":"2024-04-08","cited_by_count":30,"area":null},{"id":"2406.06843","title":"HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction","created":"2024-06-10","cited_by_count":29,"area":null},{"id":"2308.04417","title":"DiffCR: A Fast Conditional Diffusion Framework for Cloud Removal from Optical Satellite Images","created":"2023-08-08","cited_by_count":27,"area":"diffusion"},{"id":"2308.12350","title":"Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation","created":"2023-08-23","cited_by_count":27,"area":"diffusion"},{"id":"2308.13369","title":"Distribution-Aligned Diffusion for Human Mesh Recovery","created":"2023-08-25","cited_by_count":27,"area":null},{"id":"2409.13426","title":"HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Device","created":"2024-09-20","cited_by_count":27,"area":null},{"id":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2307.03833","title":"Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation","created":"2023-07-07","cited_by_count":24,"area":null},{"id":"2401.00029","title":"6D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimation","created":"2023-12-29","cited_by_count":24,"area":null},{"id":"2407.08394","title":"Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers","created":"2024-07-11","cited_by_count":24,"area":"diffusion"},{"id":"2405.05216","title":"FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models","created":"2024-05-08","cited_by_count":23,"area":"diffusion"},{"id":"2403.16198","title":"Diffusion Model is a Good Pose Estimator from 3D RF-Vision","created":"2024-03-24","cited_by_count":22,"area":"diffusion"},{"id":"2304.07574","title":"Exploring Incompatible Knowledge Transfer in Few-shot Image Generation","created":"2023-04-15","cited_by_count":19,"area":null},{"id":"2404.11291","title":"Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption","created":"2024-04-17","cited_by_count":19,"area":"diffusion"},{"id":"2502.02525","title":"Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation","created":"2025-02-04","cited_by_count":16,"area":"diffusion"},{"id":"2508.14461","title":"Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering","created":"2025-08-20","cited_by_count":16,"area":"diffusion"},{"id":"2409.10473","title":"MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion","created":"2024-09-16","cited_by_count":15,"area":"diffusion"},{"id":"2308.02963","title":"Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models","created":"2023-08-05","cited_by_count":14,"area":"diffusion"},{"id":"2406.01334","title":"HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models","created":"2024-06-03","cited_by_count":14,"area":"diffusion"},{"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":"2404.00485","title":"DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans","created":"2024-03-30","cited_by_count":13,"area":null},{"id":"2505.24315","title":"InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing","created":"2025-05-30","cited_by_count":13,"area":null},{"id":"2404.03159","title":"HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud","created":"2024-04-04","cited_by_count":12,"area":"diffusion"},{"id":"2404.01051","title":"Action Detection via an Image Diffusion Process","created":"2024-04-01","cited_by_count":11,"area":null},{"id":"2412.02903","title":"EgoCast: Forecasting Egocentric Human Pose in the Wild","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2412.10235","title":"EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modeling","created":"2024-12-13","cited_by_count":11,"area":null},{"id":"2309.01575","title":"DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion","created":"2023-09-04","cited_by_count":9,"area":"diffusion"},{"id":"2312.08825","title":"Guided Diffusion from Self-Supervised Diffusion Features","created":"2023-12-14","cited_by_count":9,"area":"diffusion"},{"id":"2411.10745","title":"Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition","created":"2024-11-16","cited_by_count":9,"area":"diffusion"},{"id":"2503.23331","title":"HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation","created":"2025-03-30","cited_by_count":8,"area":null},{"id":"2504.14335","title":"Visual Prompting for One-shot Controllable Video Editing without Inversion","created":"2025-04-19","cited_by_count":8,"area":"diffusion"},{"id":"2305.13705","title":"DiffHand: End-to-End Hand Mesh Reconstruction via Diffusion Models","created":"2023-05-23","cited_by_count":7,"area":"diffusion"},{"id":"2309.17143","title":"Revisiting Cephalometric Landmark Detection from the view of Human Pose Estimation with Lightweight Super-Resolution Head","created":"2023-09-29","cited_by_count":6,"area":null},{"id":"2310.13039","title":"Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2312.06386","title":"ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2405.05552","title":"Bidirectional Progressive Transformer for Interaction Intention Anticipation","created":"2024-05-09","cited_by_count":6,"area":null},{"id":"2504.03006","title":"DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recovery","created":"2025-04-03","cited_by_count":6,"area":null},{"id":"2306.17074","title":"Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation","created":"2023-06-29","cited_by_count":5,"area":"diffusion"},{"id":"2408.15810","title":"Multi-view Pose Fusion for Occlusion-Aware 3D Human Pose Estimation","created":"2024-08-28","cited_by_count":5,"area":null},{"id":"2409.18364","title":"Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images","created":"2024-09-27","cited_by_count":5,"area":"diffusion"},{"id":"2501.09411","title":"Towards Robust and Realistic Human Pose Estimation via WiFi Signals","created":"2025-01-16","cited_by_count":5,"area":null},{"id":"2504.10433","title":"MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model","created":"2025-04-14","cited_by_count":5,"area":"diffusion"},{"id":"2509.06956","title":"H$_{2}$OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2304.04175","title":"Token Boosting for Robust Self-Supervised Visual Transformer Pre-training","created":"2023-04-09","cited_by_count":4,"area":null},{"id":"2511.19105","title":"Graph-based 3D Human Pose Estimation using WiFi Signals","created":"2025-11-24","cited_by_count":4,"area":null},{"id":"2603.20470","title":"DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation","created":"2026-03-20","cited_by_count":4,"area":"diffusion"},{"id":"2401.08930","title":"PADS: Plug-and-Play 3D Human Pose Analysis via Diffusion Generative Modeling","created":"2024-01-17","cited_by_count":3,"area":"diffusion"},{"id":"2403.06164","title":"Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation","created":"2024-03-10","cited_by_count":3,"area":null},{"id":"2403.19919","title":"Diff-Reg v1: Diffusion Matching Model for Registration Problem","created":"2024-03-29","cited_by_count":3,"area":null},{"id":"2407.10099","title":"STGFormer: Spatio-Temporal GraphFormer for 3D Human Pose Estimation in Video","created":"2024-07-14","cited_by_count":3,"area":null},{"id":"2408.14860","title":"DiffSurf: A Transformer-based Diffusion Model for Generating and Reconstructing 3D Surfaces in Pose","created":"2024-08-27","cited_by_count":3,"area":"diffusion"},{"id":"2410.04574","title":"Enhancing 3D Human Pose Estimation Amidst Severe Occlusion with Dual Transformer Fusion","created":"2024-10-06","cited_by_count":3,"area":null},{"id":"2508.10897","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2602.05755","title":"FMPose3D: monocular 3D pose estimation via flow matching","created":"2026-02-05","cited_by_count":3,"area":"diffusion"},{"id":"2308.09523","title":"Denoising Diffusion for 3D Hand Pose Estimation from Images","created":"2023-08-18","cited_by_count":2,"area":"diffusion"},{"id":"2308.09910","title":"Physics-Guided Human Motion Capture with Pose Probability Modeling","created":"2023-08-19","cited_by_count":2,"area":null},{"id":"2401.09836","title":"Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Framework","created":"2024-01-18","cited_by_count":2,"area":null},{"id":"2402.02339","title":"Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation","created":"2024-02-04","cited_by_count":2,"area":null},{"id":"2405.17016","title":"$\\text{Di}^2\\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation","created":"2024-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2407.12579","title":"The Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation","created":"2024-07-17","cited_by_count":2,"area":"diffusion"},{"id":"2408.12747","title":"CatFree3D: Category-agnostic 3D Object Detection with Diffusion","created":"2024-08-22","cited_by_count":2,"area":null},{"id":"2410.04989","title":"Conditional Variational Autoencoders for Probabilistic Pose Regression","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2410.20731","title":"BLAPose: Enhancing 3D Human Pose Estimation with Bone Length Adjustment","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2501.15763","title":"NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimation","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2505.01726","title":"Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes","created":"2025-05-03","cited_by_count":2,"area":null},{"id":"2507.15212","title":"MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstruction","created":"2025-07-21","cited_by_count":2,"area":"ssm"},{"id":"2508.06139","title":"DiffCap: Diffusion-based Real-time Human Motion Capture using Sparse IMUs and a Monocular Camera","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2511.09502","title":"DreamPose3D: Hallucinative Diffusion with Prompt Learning for 3D Human Pose Estimation","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2512.14162","title":"FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation","created":"2025-12-16","cited_by_count":2,"area":null},{"id":"2601.16763","title":"Flow Matching for Probabilistic Monocular 3D Human Pose Estimation","created":"2026-01-23","cited_by_count":2,"area":"diffusion"},{"id":"2409.17356","title":"A vision-based framework for human behavior understanding in industrial assembly lines","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2503.09537","title":"GenHPE: Generative Counterfactuals for 3D Human Pose Estimation with Radio Frequency Signals","created":"2025-03-12","cited_by_count":1,"area":null},{"id":"2504.08175","title":"Multi-person Physics-based Pose Estimation for Combat Sports","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2603.07697","title":"Learning Context-Adaptive Motion Priors for Masked Motion Diffusion Models with Efficient Kinematic Attention Aggregation","created":"2026-03-08","cited_by_count":1,"area":"diffusion"},{"id":"2403.12440","title":"Self-learning Canonical Space for Multi-view 3D Human Pose Estimation","created":"2024-03-19","cited_by_count":0,"area":null},{"id":"2409.00449","title":"LangPose: Language-Aligned Motion for Robust 3D Human Pose Estimation","created":"2024-08-31","cited_by_count":0,"area":null},{"id":"2411.13607","title":"VioPose: Violin Performance 4D Pose Estimation by Hierarchical Audiovisual Inference","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2501.16146","title":"Toward Efficient Generalization in 3D Human Pose Estimation via a Canonical Domain Approach","created":"2025-01-27","cited_by_count":0,"area":null},{"id":"2504.01764","title":"Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2505.04276","title":"HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimation","created":"2025-05-07","cited_by_count":0,"area":"diffusion"},{"id":"2506.02853","title":"Learning Pyramid-structured Long-range Dependencies for 3D Human Pose Estimation","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2510.00527","title":"Cascaded Diffusion Framework for Probabilistic Coarse-to-Fine Hand Pose Estimation","created":"2025-10-01","cited_by_count":0,"area":"diffusion"},{"id":"2512.10321","title":"Point2Pose: A Generative Framework for 3D Human Pose Estimation with Multi-View Point Cloud Dataset","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2601.12948","title":"GazeD: Context-Aware Diffusion for Accurate 3D Gaze Estimation","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.03126","title":"Flexible Geometric Guidance for Probabilistic Human Pose Estimation with Diffusion Models","created":"2026-02-03","cited_by_count":0,"area":"diffusion"},{"id":"2602.11242","title":"ReTracing: An Archaeological Approach Through Body, Machine, and Generative Systems","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2605.25685","title":"HumanFlow -- Diffusion-Driven MAV Navigation Among Humans via Tightly-Coupled Motion Tracking, Forecasting, and Control","created":"2026-05-25","cited_by_count":0,"area":"diffusion"},{"id":"2606.22660","title":"Prompting Diffusion Models for Zero-Shot Instance Segmentation","created":"2026-06-21","cited_by_count":0,"area":"diffusion"},{"id":"2607.01990","title":"Training-free Controllable Human Motion Generation under Heterogeneous Constraints","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.09579","title":"You Only Flow Once: Calibrated and Real-Time Radar Pose Estimation with Multi-Hypothesis Normalizing Flows","created":"2026-08-10","cited_by_count":0,"area":"diffusion"},{"id":"2608.12187","title":"HSTGFormer: Hyper Spatial-Temporal Graph Transformer for 3D Human Pose Estimation","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2608.15984","title":"A Plug-and-Play 2D Motion Interface for Real-World Motion Language Models","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2610.02943","title":"Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level Privacy","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}